Search

Comparative settings (e.g. pairwise choice, listwise ranking) have been adopted by a wide range of subjective studies for image quality assessment (IQA), as it inherently standardizes the evaluation criteria across different observers and offer more clear-cut responses. In this work, we extend the edge of emerging large multi-modality models (LMMs) to further advance visual quality comparison into open-ended settings, that 1) can respond to open-range questions on quality comparison; 2) can provide detailed reasonings beyond direct answers. To this end, we propose the Co-Instruct. To train this first-of-its-kind open-source open-ended visual quality comparer, we collect the Co-Instruct-562K dataset, from two sources: (a) LLM-merged single image quality description, (b) GPT-4V "teacher" responses on unlabeled data. Furthermore, to better evaluate this setting, we propose the MICBench, the first benchmark on multi-image comparison for LMMs. We demonstrate that Co-Instruct not only achieves in average 30% higher accuracy than state-of-the-art open-source LMMs, but also outperforms GPT-4V (its teacher), on both existing related benchmarks and the proposed MICBench. Our model is published at https://huggingface.co/q-future/co-instruct., Comment: Fix typos

We provide evidence for CH-based nonconventional hydrogen bonds (H-bonds) for 10 Lewis antigens and two of their rhamnose analogues. We also characterize the thermodynamics and kinetics of the H-bonds in these molecules and present a plausible explanation for the presence of nonconventional H-bonds in Lewis antigens. Using an alternative method to simultaneously fit a series of temperature-dependent fast exchange nuclear magnetic resonance (NMR) spectra, we determined that the H-bonded conformation is favored by ∼1 kcal/mol over the non-H-bonded conformation. Additionally, a comparison of temperature-dependent 13C linewidths in various Lewis antigens and the two rhamnose analogues reveals H-bonds between the carbonyl oxygen of the N-acetyl group of N-acetylglucosamine and the OH2 group of galactose/fucose. The data presented herein provide insight into the contribution of nonconventional H-bonding to molecular structure and could therefore be used for the rational design of therapeutics.

Recent learning-based video quality assessment (VQA) algorithms are expensive to implement due to the cost of data collection of human quality opinions, and are less robust across various scenarios due to the biases of these opinions. This motivates our exploration on opinion-unaware (a.k.a zero-shot) VQA approaches. Existing approaches only considers low-level naturalness in spatial or temporal domain, without considering impacts from high-level semantics. In this work, we introduce an explicit semantic affinity index for opinion-unaware VQA using text-prompts in the contrastive language-image pre-training (CLIP) model. We also aggregate it with different traditional low-level naturalness indexes through gaussian normalization and sigmoid rescaling strategies. Composed of aggregated semantic and technical metrics, the proposed Blind Unified Opinion-Unaware Video Quality Index via Semantic and Technical Metric Aggregation (BUONA-VISTA) outperforms existing opinion-unaware VQA methods by at least 20% improvements, and is more robust than opinion-aware approaches.

The proliferation of in-the-wild videos has greatly expanded the Video Quality Assessment (VQA) problem. Unlike early definitions that usually focus on limited distortion types, VQA on in-the-wild videos is especially challenging as it could be affected by complicated factors, including various distortions and diverse contents. Though subjective studies have collected overall quality scores for these videos, how the abstract quality scores relate with specific factors is still obscure, hindering VQA methods from more concrete quality evaluations (e.g. sharpness of a video). To solve this problem, we collect over two million opinions on 4,543 in-the-wild videos on 13 dimensions of quality-related factors, including in-capture authentic distortions (e.g. motion blur, noise, flicker), errors introduced by compression and transmission, and higher-level experiences on semantic contents and aesthetic issues (e.g. composition, camera trajectory), to establish the multi-dimensional Maxwell database. Specifically, we ask the subjects to label among a positive, a negative, and a neutral choice for each dimension. These explanation-level opinions allow us to measure the relationships between specific quality factors and abstract subjective quality ratings, and to benchmark different categories of VQA algorithms on each dimension, so as to more comprehensively analyze their strengths and weaknesses. Furthermore, we propose the MaxVQA, a language-prompted VQA approach that modifies vision-language foundation model CLIP to better capture important quality issues as observed in our analyses. The MaxVQA can jointly evaluate various specific quality factors and final quality scores with state-of-the-art accuracy on all dimensions, and superb generalization ability on existing datasets. Code and data available at https://github.com/VQAssessment/MaxVQA., Comment: Proceedings of the 31st ACM International Conference on Multimedia (MM '23)

Multi-view clustering can partition data samples into their categories by learning a consensus representation in unsupervised way and has received more and more attention in recent years. However, most existing deep clustering methods learn consensus representation or view-specific representations from multiple views via view-wise aggregation way, where they ignore structure relationship of all samples. In this paper, we propose a novel multi-view clustering network to address these problems, called Global and Cross-view Feature Aggregation for Multi-View Clustering (GCFAggMVC). Specifically, the consensus data presentation from multiple views is obtained via cross-sample and cross-view feature aggregation, which fully explores the complementary ofsimilar samples. Moreover, we align the consensus representation and the view-specific representation by the structure-guided contrastive learning module, which makes the view-specific representations from different samples with high structure relationship similar. The proposed module is a flexible multi-view data representation module, which can be also embedded to the incomplete multi-view data clustering task via plugging our module into other frameworks. Extensive experiments show that the proposed method achieves excellent performance in both complete multi-view data clustering tasks and incomplete multi-view data clustering tasks.

The proliferation of videos collected during in-the-wild natural settings has pushed the development of effective Video Quality Assessment (VQA) methodologies. Contemporary supervised opinion-driven VQA strategies predominantly hinge on training from expensive human annotations for quality scores, which limited the scale and distribution of VQA datasets and consequently led to unsatisfactory generalization capacity of methods driven by these data. On the other hand, although several handcrafted zero-shot quality indices do not require training from human opinions, they are unable to account for the semantics of videos, rendering them ineffective in comprehending complex authentic distortions (e.g., white balance, exposure) and assessing the quality of semantic content within videos. To address these challenges, we introduce the text-prompted Semantic Affinity Quality Index (SAQI) and its localized version (SAQI-Local) using Contrastive Language-Image Pre-training (CLIP) to ascertain the affinity between textual prompts and visual features, facilitating a comprehensive examination of semantic quality concerns without the reliance on human quality annotations. By amalgamating SAQI with existing low-level metrics, we propose the unified Blind Video Quality Index (BVQI) and its improved version, BVQI-Local, which demonstrates unprecedented performance, surpassing existing zero-shot indices by at least 24\% on all datasets. Moreover, we devise an efficient fine-tuning scheme for BVQI-Local that jointly optimizes text prompts and final fusion weights, resulting in state-of-the-art performance and superior generalization ability in comparison to prevalent opinion-driven VQA methods. We conduct comprehensive analyses to investigate different quality concerns of distinct indices, demonstrating the effectiveness and rationality of our design., Comment: 13 pages, 10 figures, under review

The explosion of visual content available online underscores the requirement for an accurate machine assessor to robustly evaluate scores across diverse types of visual contents. While recent studies have demonstrated the exceptional potentials of large multi-modality models (LMMs) on a wide range of related fields, in this work, we explore how to teach them for visual rating aligned with human opinions. Observing that human raters only learn and judge discrete text-defined levels in subjective studies, we propose to emulate this subjective process and teach LMMs with text-defined rating levels instead of scores. The proposed Q-Align achieves state-of-the-art performance on image quality assessment (IQA), image aesthetic assessment (IAA), as well as video quality assessment (VQA) tasks under the original LMM structure. With the syllabus, we further unify the three tasks into one model, termed the OneAlign. In our experiments, we demonstrate the advantage of the discrete-level-based syllabus over direct-score-based variants for LMMs. Our code and the pre-trained weights are released at https://github.com/Q-Future/Q-Align., Comment: Technical Report

Real-world image super-resolution (RWSR) is a long-standing problem as low-quality (LQ) images often have complex and unidentified degradations. Existing methods such as Generative Adversarial Networks (GANs) or continuous diffusion models present their own issues including GANs being difficult to train while continuous diffusion models requiring numerous inference steps. In this paper, we propose an Iterative Token Evaluation and Refinement (ITER) framework for RWSR, which utilizes a discrete diffusion model operating in the discrete token representation space, i.e., indexes of features extracted from a VQGAN codebook pre-trained with high-quality (HQ) images. We show that ITER is easier to train than GANs and more efficient than continuous diffusion models. Specifically, we divide RWSR into two sub-tasks, i.e., distortion removal and texture generation. Distortion removal involves simple HQ token prediction with LQ images, while texture generation uses a discrete diffusion model to iteratively refine the distortion removal output with a token refinement network. In particular, we propose to include a token evaluation network in the discrete diffusion process. It learns to evaluate which tokens are good restorations and helps to improve the iterative refinement results. Moreover, the evaluation network can first check status of the distortion removal output and then adaptively select total refinement steps needed, thereby maintaining a good balance between distortion removal and texture generation. Extensive experimental results show that ITER is easy to train and performs well within just 8 iterative steps. Our codes will be available publicly., Comment: To appear in AAAI2024, https://github.com/chaofengc/ITER

Text-to-image diffusion models are typically trained to optimize the log-likelihood objective, which presents challenges in meeting specific requirements for downstream tasks, such as image aesthetics and image-text alignment. Recent research addresses this issue by refining the diffusion U-Net using human rewards through reinforcement learning or direct backpropagation. However, many of them overlook the importance of the text encoder, which is typically pretrained and fixed during training. In this paper, we demonstrate that by finetuning the text encoder through reinforcement learning, we can enhance the text-image alignment of the results, thereby improving the visual quality. Our primary motivation comes from the observation that the current text encoder is suboptimal, often requiring careful prompt adjustment. While fine-tuning the U-Net can partially improve performance, it remains suffering from the suboptimal text encoder. Therefore, we propose to use reinforcement learning with low-rank adaptation to finetune the text encoder based on task-specific rewards, referred as \textbf{TexForce}. We first show that finetuning the text encoder can improve the performance of diffusion models. Then, we illustrate that TexForce can be simply combined with existing U-Net finetuned models to get much better results without additional training. Finally, we showcase the adaptability of our method in diverse applications, including the generation of high-quality face and hand images.

Multi-modality foundation models, as represented by GPT-4V, have brought a new paradigm for low-level visual perception and understanding tasks, that can respond to a broad range of natural human instructions in a model. While existing foundation models have shown exciting potentials on low-level visual tasks, their related abilities are still preliminary and need to be improved. In order to enhance these models, we conduct a large-scale subjective experiment collecting a vast number of real human feedbacks on low-level vision. Each feedback follows a pathway that starts with a detailed description on the low-level visual appearance (*e.g. clarity, color, brightness* of an image, and ends with an overall conclusion, with an average length of 45 words. The constructed **Q-Pathway** dataset includes 58K detailed human feedbacks on 18,973 images with diverse low-level appearance. Moreover, to enable foundation models to robustly respond to diverse types of questions, we design a GPT-participated conversion to process these feedbacks into diverse-format 200K instruction-response pairs. Experimental results indicate that the **Q-Instruct** consistently elevates low-level perception and understanding abilities across several foundational models. We anticipate that our datasets can pave the way for a future that general intelligence can perceive, understand low-level visual appearance and evaluate visual quality like a human. Our dataset, model zoo, and demo is published at: https://q-future.github.io/Q-Instruct., Comment: 16 pages, 11 figures, page 12-16 as appendix

When some application scenarios need to use semantic segmentation technology, like automatic driving, the primary concern comes to real-time performance rather than extremely high segmentation accuracy. To achieve a good trade-off between speed and accuracy, two-branch architecture has been proposed in recent years. It treats spatial information and semantics information separately which allows the model to be composed of two networks both not heavy. However, the process of fusing features with two different scales becomes a performance bottleneck for many nowaday two-branch models. In this research, we design a new fusion mechanism for two-branch architecture which is guided by attention computation. To be precise, we use the Dual-Guided Attention (DGA) module we proposed to replace some multi-scale transformations with the calculation of attention which means we only use several attention layers of near linear complexity to achieve performance comparable to frequently-used multi-layer fusion. To ensure that our module can be effective, we use Residual U-blocks (RSU) to build one of the two branches in our networks which aims to obtain better multi-scale features. Extensive experiments on Cityscapes and CamVid dataset show the effectiveness of our method.

The rapid evolution of Multi-modality Large Language Models (MLLMs) has catalyzed a shift in computer vision from specialized models to general-purpose foundation models. Nevertheless, there is still an inadequacy in assessing the abilities of MLLMs on low-level visual perception and understanding. To address this gap, we present Q-Bench, a holistic benchmark crafted to systematically evaluate potential abilities of MLLMs on three realms: low-level visual perception, low-level visual description, and overall visual quality assessment. a) To evaluate the low-level perception ability, we construct the LLVisionQA dataset, consisting of 2,990 diverse-sourced images, each equipped with a human-asked question focusing on its low-level attributes. We then measure the correctness of MLLMs on answering these questions. b) To examine the description ability of MLLMs on low-level information, we propose the LLDescribe dataset consisting of long expert-labelled golden low-level text descriptions on 499 images, and a GPT-involved comparison pipeline between outputs of MLLMs and the golden descriptions. c) Besides these two tasks, we further measure their visual quality assessment ability to align with human opinion scores. Specifically, we design a softmax-based strategy that enables MLLMs to predict quantifiable quality scores, and evaluate them on various existing image quality assessment (IQA) datasets. Our evaluation across the three abilities confirms that MLLMs possess preliminary low-level visual skills. However, these skills are still unstable and relatively imprecise, indicating the need for specific enhancements on MLLMs towards these abilities. We hope that our benchmark can encourage the research community to delve deeper to discover and enhance these untapped potentials of MLLMs. Project Page: https://q-future.github.io/Q-Bench., Comment: 27 pages, 11 tables, with updated results

Image Quality Assessment (IQA) constitutes a fundamental task within the field of computer vision, yet it remains an unresolved challenge, owing to the intricate distortion conditions, diverse image contents, and limited availability of data. Recently, the community has witnessed the emergence of numerous large-scale pretrained foundation models, which greatly benefit from dramatically increased data and parameter capacities. However, it remains an open problem whether the scaling law in high-level tasks is also applicable to IQA task which is closely related to low-level clues. In this paper, we demonstrate that with proper injection of local distortion features, a larger pretrained and fixed foundation model performs better in IQA tasks. Specifically, for the lack of local distortion structure and inductive bias of vision transformer (ViT), alongside the large-scale pretrained ViT, we use another pretrained convolution neural network (CNN), which is well known for capturing the local structure, to extract multi-scale image features. Further, we propose a local distortion extractor to obtain local distortion features from the pretrained CNN and a local distortion injector to inject the local distortion features into ViT. By only training the extractor and injector, our method can benefit from the rich knowledge in the powerful foundation models and achieve state-of-the-art performance on popular IQA datasets, indicating that IQA is not only a low-level problem but also benefits from stronger high-level features drawn from large-scale pretrained models.

Image Quality Assessment (IQA) is a fundamental task in computer vision that has witnessed remarkable progress with deep neural networks. Inspired by the characteristics of the human visual system, existing methods typically use a combination of global and local representations (\ie, multi-scale features) to achieve superior performance. However, most of them adopt simple linear fusion of multi-scale features, and neglect their possibly complex relationship and interaction. In contrast, humans typically first form a global impression to locate important regions and then focus on local details in those regions. We therefore propose a top-down approach that uses high-level semantics to guide the IQA network to focus on semantically important local distortion regions, named as \emph{TOPIQ}. Our approach to IQA involves the design of a heuristic coarse-to-fine network (CFANet) that leverages multi-scale features and progressively propagates multi-level semantic information to low-level representations in a top-down manner. A key component of our approach is the proposed cross-scale attention mechanism, which calculates attention maps for lower level features guided by higher level features. This mechanism emphasizes active semantic regions for low-level distortions, thereby improving performance. CFANet can be used for both Full-Reference (FR) and No-Reference (NR) IQA. We use ResNet50 as its backbone and demonstrate that CFANet achieves better or competitive performance on most public FR and NR benchmarks compared with state-of-the-art methods based on vision transformers, while being much more efficient (with only ${\sim}13\%$ FLOPS of the current best FR method). Codes are released at \url{https://github.com/chaofengc/IQA-PyTorch}., Comment: 13 pages, 8 figures, 10 tables. In submission

To improve the accuracy of color image completion with missing entries, we present a recovery method based on generalized higher-order scalars. We extend the traditional second-order matrix model to a more comprehensive higher-order matrix equivalent, called the "t-matrix" model, which incorporates a pixel neighborhood expansion strategy to characterize the local pixel constraints. This "t-matrix" model is then used to extend some commonly used matrix and tensor completion algorithms to their higher-order versions. We perform extensive experiments on various algorithms using simulated data and algorithms on simulated data and publicly available images and compare their performance. The results show that our generalized matrix completion model and the corresponding algorithm compare favorably with their lower-order tensor and conventional matrix counterparts., Comment: 24 pages; 9 figures

Image inpainting for completing complicated semantic environments and diverse hole patterns of corrupted images is challenging even for state-of-the-art learning-based inpainting methods trained on large-scale data. A reference image capturing the same scene of a corrupted image offers informative guidance for completing the corrupted image as it shares similar texture and structure priors to that of the holes of the corrupted image. In this work, we propose a transformer-based encoder-decoder network, named TransRef, for reference-guided image inpainting. Specifically, the guidance is conducted progressively through a reference embedding procedure, in which the referencing features are subsequently aligned and fused with the features of the corrupted image. For precise utilization of the reference features for guidance, a reference-patch alignment (Ref-PA) module is proposed to align the patch features of the reference and corrupted images and harmonize their style differences, while a reference-patch transformer (Ref-PT) module is proposed to refine the embedded reference feature. Moreover, to facilitate the research of reference-guided image restoration tasks, we construct a publicly accessible benchmark dataset containing 50K pairs of input and reference images. Both quantitative and qualitative evaluations demonstrate the efficacy of the reference information and the proposed method over the state-of-the-art methods in completing complex holes. Code and dataset can be accessed at https://github.com/Cameltr/TransRef., Comment: Under review

Low-quality multimedia data (including low resolution, low illumination, defects, blurriness, etc.) often pose a challenge for content understanding, as algorithms are typically developed under ideal conditions (high resolution and good visibility). To alleviate this problem, data enhancement techniques (e.g., super-resolution, low-light enhancement, derain, and inpainting) have been proposed to restore low-quality multimedia data. Efforts are also being made to develop robust content understanding algorithms in adverse weather and lighting conditions. Some quality assessment techniques aiming at evaluating the analytical quality of data have also emerged. Even though these topics are mostly studied independently, they are tightly related in terms of ensuring a robust understanding of multimedia content. For example, enhancement should maintain the semantic consistency of the analysis, while quality assessment should consider the comprehensibility of the multimedia data. The purpose of this workshop is to bring together individuals in three areas: enhancement, analysis, and evaluation, for sharing ideas and discussion on current developments and future directions. © 2022 Owner/Author.

The rapid increase in user-generated-content (UGC) videos calls for the development of effective video quality assessment (VQA) algorithms. However, the objective of the UGC-VQA problem is still ambiguous and can be viewed from two perspectives: the technical perspective, measuring the perception of distortions; and the aesthetic perspective, which relates to preference and recommendation on contents. To understand how these two perspectives affect overall subjective opinions in UGC-VQA, we conduct a large-scale subjective study to collect human quality opinions on overall quality of videos as well as perceptions from aesthetic and technical perspectives. The collected Disentangled Video Quality Database (DIVIDE-3k) confirms that human quality opinions on UGC videos are universally and inevitably affected by both aesthetic and technical perspectives. In light of this, we propose the Disentangled Objective Video Quality Evaluator (DOVER) to learn the quality of UGC videos based on the two perspectives. The DOVER proves state-of-the-art performance in UGC-VQA under very high efficiency. With perspective opinions in DIVIDE-3k, we further propose DOVER++, the first approach to provide reliable clear-cut quality evaluations from a single aesthetic or technical perspective. Code at https://github.com/VQAssessment/DOVER.

The increased resolution of real-world videos presents a dilemma between efficiency and accuracy for deep Video Quality Assessment (VQA). On the one hand, keeping the original resolution will lead to unacceptable computational costs. On the other hand, existing practices, such as resizing and cropping, will change the quality of original videos due to the loss of details and contents, and are therefore harmful to quality assessment. With the obtained insight from the study of spatial-temporal redundancy in the human visual system and visual coding theory, we observe that quality information around a neighbourhood is typically similar, motivating us to investigate an effective quality-sensitive neighbourhood representatives scheme for VQA. In this work, we propose a unified scheme, spatial-temporal grid mini-cube sampling (St-GMS) to get a novel type of sample, named fragments. Full-resolution videos are first divided into mini-cubes with preset spatial-temporal grids, then the temporal-aligned quality representatives are sampled to compose the fragments that serve as inputs for VQA. In addition, we design the Fragment Attention Network (FANet), a network architecture tailored specifically for fragments. With fragments and FANet, the proposed efficient end-to-end FAST-VQA and FasterVQA achieve significantly better performance than existing approaches on all VQA benchmarks while requiring only 1/1612 FLOPs compared to the current state-of-the-art. Codes, models and demos are available at https://github.com/timothyhtimothy/FAST-VQA-and-FasterVQA.

Existing learning-based image inpainting methods are still in challenge when facing complex semantic environments and diverse hole patterns. The prior information learned from the large scale training data is still insufficient for these situations. Reference images captured covering the same scenes share similar texture and structure priors with the corrupted images, which offers new prospects for the image inpainting tasks. Inspired by this, we first build a benchmark dataset containing 10K pairs of input and reference images for reference-guided inpainting. Then we adopt an encoder-decoder structure to separately infer the texture and structure features of the input image considering their pattern discrepancy of texture and structure during inpainting. A feature alignment module is further designed to refine these features of the input image with the guidance of a reference image. Both quantitative and qualitative evaluations demonstrate the superiority of our method over the state-of-the-art methods in terms of completing complex holes., Comment: IEEE International Conference on Image Processing(ICIP 2022)

With the rapid growth of in-the-wild videos taken by non-specialists, blind video quality assessment (VQA) has become a challenging and demanding problem. Although lots of efforts have been made to solve this problem, it remains unclear how the human visual system (HVS) relates to the temporal quality of videos. Meanwhile, recent work has found that the frames of natural video transformed into the perceptual domain of the HVS tend to form a straight trajectory of the representations. With the obtained insight that distortion impairs the perceived video quality and results in a curved trajectory of the perceptual representation, we propose a temporal perceptual quality index (TPQI) to measure the temporal distortion by describing the graphic morphology of the representation. Specifically, we first extract the video perceptual representations from the lateral geniculate nucleus (LGN) and primary visual area (V1) of the HVS, and then measure the straightness and compactness of their trajectories to quantify the degradation in naturalness and content continuity of video. Experiments show that the perceptual representation in the HVS is an effective way of predicting subjective temporal quality, and thus TPQI can, for the first time, achieve comparable performance to the spatial quality metric and be even more effective in assessing videos with large temporal variations. We further demonstrate that by combining with NIQE, a spatial quality metric, TPQI can achieve top performance over popular in-the-wild video datasets. More importantly, TPQI does not require any additional information beyond the video being evaluated and thus can be applied to any datasets without parameter tuning. Source code is available at https://github.com/UoLMM/TPQI-VQA., Comment: Will appear on ACM MM 2022

Current deep video quality assessment (VQA) methods are usually with high computational costs when evaluating high-resolution videos. This cost hinders them from learning better video-quality-related representations via end-to-end training. Existing approaches typically consider naive sampling to reduce the computational cost, such as resizing and cropping. However, they obviously corrupt quality-related information in videos and are thus not optimal for learning good representations for VQA. Therefore, there is an eager need to design a new quality-retained sampling scheme for VQA. In this paper, we propose Grid Mini-patch Sampling (GMS), which allows consideration of local quality by sampling patches at their raw resolution and covers global quality with contextual relations via mini-patches sampled in uniform grids. These mini-patches are spliced and aligned temporally, named as fragments. We further build the Fragment Attention Network (FANet) specially designed to accommodate fragments as inputs. Consisting of fragments and FANet, the proposed FrAgment Sample Transformer for VQA (FAST-VQA) enables efficient end-to-end deep VQA and learns effective video-quality-related representations. It improves state-of-the-art accuracy by around 10% while reducing 99.5% FLOPs on 1080P high-resolution videos. The newly learned video-quality-related representations can also be transferred into smaller VQA datasets, boosting performance in these scenarios. Extensive experiments show that FAST-VQA has good performance on inputs of various resolutions while retaining high efficiency. We publish our code at https://github.com/timothyhtimothy/FAST-VQA., Comment: Will appear on ECCV 2022. 14 Pages

Spatial-Temporal Video Super-Resolution (ST-VSR) aims to generate super-resolved videos with higher resolution(HR) and higher frame rate (HFR). Quite intuitively, pioneering two-stage based methods complete ST-VSR by directly combining two sub-tasks: Spatial Video Super-Resolution (S-VSR) and Temporal Video Super-Resolution(T-VSR) but ignore the reciprocal relations among them. Specifically, 1) T-VSR to S-VSR: temporal correlations help accurate spatial detail representation with more clues; 2) S-VSR to T-VSR: abundant spatial information contributes to the refinement of temporal prediction. To this end, we propose a one-stage based Cycle-projected Mutual learning network (CycMu-Net) for ST-VSR, which makes full use of spatial-temporal correlations via the mutual learning between S-VSR and T-VSR. Specifically, we propose to exploit the mutual information among them via iterative up-and-down projections, where the spatial and temporal features are fully fused and distilled, helping the high-quality video reconstruction. Besides extensive experiments on benchmark datasets, we also compare our proposed CycMu-Net with S-VSR and T-VSR tasks, demonstrating that our method significantly outperforms state-of-the-art methods., Comment: 10 pages, 8 figures

Low-rank approximation of images via singular value decomposition is well-received in the era of big data. However, singular value decomposition (SVD) is only for order-two data, i.e., matrices. It is necessary to flatten a higher order input into a matrix or break it into a series of order-two slices to tackle higher order data such as multispectral images and videos with the SVD. Higher order singular value decomposition (HOSVD) extends the SVD and can approximate higher order data using sums of a few rank-one components. We consider the problem of generalizing HOSVD over a finite dimensional commutative algebra. This algebra, referred to as a t-algebra, generalizes the field of complex numbers. The elements of the algebra, called t-scalars, are fix-sized arrays of complex numbers. One can generalize matrices and tensors over t-scalars and then extend many canonical matrix and tensor algorithms, including HOSVD, to obtain higher-performance versions. The generalization of HOSVD is called THOSVD. Its performance of approximating multi-way data can be further improved by an alternating algorithm. THOSVD also unifies a wide range of principal component analysis algorithms. To exploit the potential of generalized algorithms using t-scalars for approximating images, we use a pixel neighborhood strategy to convert each pixel to "deeper-order" t-scalar. Experiments on publicly available images show that the generalized algorithm over t-scalars, namely THOSVD, compares favorably with its canonical counterparts., Comment: 21 pages, 11 figures, several typos in the appendix corrected

The temporal relationships between frames and their influences on video quality assessment (VQA) are still under-studied in existing works. These relationships lead to two important types of effects for video quality. Firstly, some temporal variations (such as shaking, flicker, and abrupt scene transitions) are causing temporal distortions and lead to extra quality degradations, while other variations (e.g. those related to meaningful happenings) do not. Secondly, the human visual system often has different attention to frames with different contents, resulting in their different importance to the overall video quality. Based on prominent time-series modeling ability of transformers, we propose a novel and effective transformer-based VQA method to tackle these two issues. To better differentiate temporal variations and thus capture the temporal distortions, we design a transformer-based Spatial-Temporal Distortion Extraction (STDE) module. To tackle with temporal quality attention, we propose the encoder-decoder-like temporal content transformer (TCT). We also introduce the temporal sampling on features to reduce the input length for the TCT, so as to improve the learning effectiveness and efficiency of this module. Consisting of the STDE and the TCT, the proposed Temporal Distortion-Content Transformers for Video Quality Assessment (DisCoVQA) reaches state-of-the-art performance on several VQA benchmarks without any extra pre-training datasets and up to 10% better generalization ability than existing methods. We also conduct extensive ablation experiments to prove the effectiveness of each part in our proposed model, and provide visualizations to prove that the proposed modules achieve our intention on modeling these temporal issues. We will publish our codes and pretrained weights later.

Understanding foggy image sequence in the driving scenes is critical for autonomous driving, but it remains a challenging task due to the difficulty in collecting and annotating real-world images of adverse weather. Recently, the self-training strategy has been considered a powerful solution for unsupervised domain adaptation, which iteratively adapts the model from the source domain to the target domain by generating target pseudo labels and re-training the model. However, the selection of confident pseudo labels inevitably suffers from the conflict between sparsity and accuracy, both of which will lead to suboptimal models. To tackle this problem, we exploit the characteristics of the foggy image sequence of driving scenes to densify the confident pseudo labels. Specifically, based on the two discoveries of local spatial similarity and adjacent temporal correspondence of the sequential image data, we propose a novel Target-Domain driven pseudo label Diffusion (TDo-Dif) scheme. It employs superpixels and optical flows to identify the spatial similarity and temporal correspondence, respectively and then diffuses the confident but sparse pseudo labels within a superpixel or a temporal corresponding pair linked by the flow. Moreover, to ensure the feature similarity of the diffused pixels, we introduce local spatial similarity loss and temporal contrastive loss in the model re-training stage. Experimental results show that our TDo-Dif scheme helps the adaptive model achieve 51.92% and 53.84% mean intersection-over-union (mIoU) on two publicly available natural foggy datasets (Foggy Zurich and Foggy Driving), which exceeds the state-of-the-art unsupervised domain adaptive semantic segmentation methods. Models and data can be found at https://github.com/velor2012/TDo-Dif., Comment: IEEE Transactions on Image Processing 2022

Principal Component Analysis (PCA) is well known for its capability of dimension reduction and data compression. However, when using PCA for compressing/reconstructing images, images need to be recast to vectors. The vectorization of images makes some correlation constraints of neighboring pixels and spatial information lost. To deal with the drawbacks of the vectorizations adopted by PCA, we used small neighborhoods of each pixel to form compounded pixels and use a tensorial version of PCA, called TPCA (Tensorial Principal Component Analysis), to compress and reconstruct a compounded image of compounded pixels. Our experiments on public data show that TPCA compares favorably with PCA in compressing and reconstructing images. We also show in our experiments that the performance of TPCA increases when the order of compounded pixels increases., Comment: 6 pages, 4 figures, 3 tables

Ice clouds and falling snow are ubiquitous globally and play important roles in the Earth's radiation budget and precipitation processes. Ice particle microphysical properties (e.g., size, habit and orientation) are not only influenced by the ambient environment's dynamic and thermodynamic conditions, but are also intimately connected to the cloud radiative effects and particle fall speeds, which therefore have an impact on future climate projection as well as on the details of the surface precipitation (e.g., onset time, location, type and strength). Our previous work revealed that high-frequency (> 150 GHz) polarimetric radiance difference (PD) from passive microwave sensors is a good indicator of the bulk aspect ratio of horizontally oriented ice particles that often occur inside anvil clouds and/or stratiform precipitation. In this current work, we further investigate the dynamic and thermodynamic mechanisms and cloud-precipitation structures associated with ice-phase microphysics corresponding to different PD signals. In order to do so, collocated CloudSat radar (W-band) and Global Precipitation Measurement Dual-frequency Precipitation Radar (GPM DPR, Ku-Ka-bands) observations as well as European Centre for Medium-Range Weather Forecasts (ECMWF) atmosphere background profiles are grouped according to the magnitude of PD for only stratiform precipitation and/or anvil cloud scenes. We found that horizontally oriented snow aggregates or large snow particles are likely the major contributor to the high-PD signals at 166 GHz, while low-PD magnitudes can be attributed to small cloud ice, randomly oriented snow aggregates, riming snow or supercooled water. Further, high-PD (low-PD) scenes are found to be associated with stronger (weaker) wind shear and higher (lower) ambient humidity, both of which help promote (prohibit) the growth of frozen particles and the organization of convective systems. An ensemble of squall line cases is studied at the end to demonstrate tha

Completing a corrupted image with correct structures and reasonable textures for a mixed scene remains an elusive challenge. Since the missing hole in a mixed scene of a corrupted image often contains various semantic information, conventional two-stage approaches utilizing structural information often lead to the problem of unreliable structural prediction and ambiguous image texture generation. In this paper, we propose a Semantic Guidance and Evaluation Network (SGE-Net) to iteratively update the structural priors and the inpainted image in an interplay framework of semantics extraction and image inpainting. It utilizes semantic segmentation map as guidance in each scale of inpainting, under which location-dependent inferences are re-evaluated, and, accordingly, poorly-inferred regions are refined in subsequent scales. Extensive experiments on real-world images of mixed scenes demonstrated the superiority of our proposed method over state-of-the-art approaches, in terms of clear boundaries and photo-realistic textures.

We consider the problems of classification and intrinsic dimension estimation on image data. A new subspace based classifier is proposed for supervised classification or intrinsic dimension estimation. The distribution of the data in each class is modeled by a union of of a finite number ofaffine subspaces of the feature space. The affine subspaces have a common dimension, which is assumed to be much less than the dimension of the feature space. The subspaces are found using regression based on the L0-norm. The proposed method is a generalisation of classical NN (Nearest Neighbor), NFL (Nearest Feature Line) classifiers and has a close relationship to NS (Nearest Subspace) classifier. The proposed classifier with an accurately estimated dimension parameter generally outperforms its competitors in terms of classification accuracy. We also propose a fast version of the classifier using a neighborhood representation to reduce its computational complexity. Experiments on publicly available datasets corroborate these claims., Comment: 19 pages, 7 figures, 4 tables

Higher order data is modeled using matrices whose entries are numerical arrays of a fixed size. These arrays, called t-scalars, form a commutative ring under the convolution product. Matrices with elements in the ring of t-scalars are referred to as t-matrices. The t-matrices can be scaled, added and multiplied in the usual way. There are t-matrix generalizations of positive matrices, orthogonal matrices and Hermitian symmetric matrices. With the t-matrix model, it is possible to generalize many well-known matrix algorithms. In particular, the t-matrices are used to generalize the SVD (Singular Value Decomposition), HOSVD (High Order SVD), PCA (Principal Component Analysis), 2DPCA (Two Dimensional PCA) and GCA (Grassmannian Component Analysis). The generalized t-matrix algorithms, namely TSVD, THOSVD,TPCA, T2DPCA and TGCA, are applied to low-rank approximation, reconstruction,and supervised classification of images. Experiments show that the t-matrix algorithms compare favorably with standard matrix algorithms., Comment: 42 pages, 17 figures

Existing inpainting methods have achieved promising performance in recovering defected images of specific scenes. However, filling holes involving multiple semantic categories remains challenging due to the obscure semantic boundaries and the mixture of different semantic textures. In this paper, we introduce coherence priors between the semantics and textures which make it possible to concentrate on completing separate textures in a semantic-wise manner. Specifically, we adopt a multi-scale joint optimization framework to first model the coherence priors and then accordingly interleavingly optimize image inpainting and semantic segmentation in a coarse-to-fine manner. A Semantic-Wise Attention Propagation (SWAP) module is devised to refine completed image textures across scales by exploring non-local semantic coherence, which effectively mitigates mix-up of textures. We also propose two coherence losses to constrain the consistency between the semantics and the inpainted image in terms of the overall structure and detailed textures. Experimental results demonstrate the superiority of our proposed method for challenging cases with complex holes.

We consider a novel backward-compatible paradigm of general data analytics over a recently-reported semisimple algebra (called t-algebra). We study the abstract algebraic framework over the t-algebra by representing the elements of t-algebra by fix-sized multi-way arrays of complex numbers and the algebraic structure over the t-algebra by a collection of direct-product constituents. Over the t-algebra, many algorithms are generalized in a straightforward manner using this new semisimple paradigm. To demonstrate the new paradigm's performance and its backward-compatibility, we generalize some canonical algorithms for visual pattern analysis. Experiments on public datasets show that the generalized algorithms compare favorably with their canonical counterparts., Comment: 38 page, 12 figures. two typos are removed. Official code repository: https://github.com/liaoliang2020/talgebra

A non-fullerene electron acceptor bearing a fused 10-heterocyclic ring (indacenodithiophenoindacenodithiophene) with a narrow band gap (similar to 1.5 eV) was designed and synthesized. It possesses excellent planarity and enhanced effective conjugation length compared to previously reported fused-ring electron acceptors. When this acceptor was paired with PTB7-Th and applied in polymer solar cells, a power conversion efficiency of 6.5% was achieved with a high open circuit voltage of 0.94 V. More significantly, an energy loss as low as 0.59 eV and an external quantum efficiency as high as 63% were obtained simultaneously., Funding Agencies|National Natural Science Foundation of China [21504062, 21202114, 21204054, 51303118, 91333204]; Natural Science Foundation of Jiangsu Province [BK20130289]; China Postdoctoral Science Foundation Funded Project [2015M581853]; Jiangsu Province Postdoctoral Science Foundation Funded Project [1501024B]; Priority Academic Program Development of Jiangsu Higher Education Institutions; Programs Foundation of the Ministry of Education of China [20133201120008]; Beijing National Laboratory for Molecular Sciences [20140112]; State and Local Joint Engineering Laboratory for Novel Functional Polymeric Materials; CSC; Open Research Fund of State Key Lab of Silicon Materials (Zhejiang University); Knut and Alice Wallenberg foundation; Science Council, Sweden

A non-fullerene electron acceptor bearing a novel backbone with fused 10-heterocyclic ring (in-dacenodithiopheno-indacenodiselenophene), denoted by IDTIDSe-IC is developed for fullerene free polymer solar cells. IDTIDSe-IC exhibits a low band gap (E-g=1.52 eV) and strong absorption in the 600850 nm region. Combining with a large band gap polymer J51 (E-g=1.91 eV) as donor, broad absorption coverage from 300 nm to 800 nm is obtained due to complementary absorption of J51 and IDTIDSe-IC, which enables a high PCE of 8.02% with a V-oc of 0.91 V, a J(SC) of 15.16 mA/cm(2) and a FF of 58.0% in the corresponding PSCs. Moreover, the EQE of 50-65% is achieved in the absorption range of IDTIDSe-IC with only about 0.1 eV HOMO difference between J51 and IDTIDSe-IC. (C) 2016 Elsevier Ltd. All rights reserved., Funding Agencies|National Natural Science Foundation of China [21504062, 21572152]; China Postdoctoral Science Foundation [2015M581853]; Jiangsu Province Postdoctoral Science Foundation [1501024B]; Vinnova [2015-04751]; China Scholarship Council (CSC) [201306730002]; Swedish Research Council (VR) [621-2013-5561]; Swedish Energy Agency [EM 42033-1]; Swedish Government Strategic Research Area in Materials Science on Functional Materials at Linkoping University (Faculty Grant SFO-Mat-LiU) [2009 00971]; Collaborative Innovation Center of Suzhou Nano Science and Technology; Priority Academic Program Development of Jiangsu Higher Education Institutions (PAPD)

CH3NH3PbI3 is commonly used in perovskite solar cells due to its long diffusion length and good crystallinity. In this paper, in the one-step approach using CH3NH3I and PbCl2 for forming the perovskite, we present a new low temperature annealing approach of gradually increasing the temperature to fabricate perovskite films. Various temperatures and temperature ranges for the formation of perovskite films have been studied. Using the gradual annealing process, we can tune the amount of chlorine in the atomic ratio of chlorine/iodine from 1.2 to 4.0%. Meanwhile, the gradual annealing process influences the quality of the perovskite film and importantly the device performance. The results show that through the optimized process, the film quality is improved with high surface coverage and good photoluminescence and reproducibility. We find that a higher amount of chlorine in the perovskite film plays a positive role in the device performance in the approach for achieving a power conversion efficiency of 14.9% with no obvious hysteresis.

學科教學知識（PCK）是上世紀80年代提出的一種與教師課堂實踐緊密聯繫的知識。回顧學科教學知識的研究文獻發現，較少有研究專門針對學科教學知識轉化為課堂教學行為的過程。本研究選取三位中學化學教師作為案例，詳細描述和分析了PCK如何向課堂教學進行轉化。根據PCK的兩大維度一是關於“教"，二是關於“內容"，研究選擇了某一特定教學主題（化學反應速率）以及探究式教學來具體化這兩大維度。這樣研究就是從具有特定教學主題和教學取向的角度去闡釋PCK的轉化過程。轉化研究從四個方面進行展開：一是教師對於探究的知識和信念，二是以探究為教學取向的PCK，三是教師的課堂實踐行為，四是PCK與教學行為之間的聯繫和差異，以及影響PCK向課堂實踐轉化的因素。, 研究發現PCK向課堂實踐的轉化，可以從三個方面進行闡釋。首先從教師所理解的探究知識而言，教師對探究的理解程度會影響教學目標的制定、教學內容的選擇、教學策略和教學評價的實施以及學生知識這些PCK的主要成分，繼而影響探究教學的實施。教師對探究的理解最主要的困難體現在三個方面：一是缺乏使用證據進行解釋的意識；二是將探究等同於“預測"、“實驗室活動"；三是重視“做"科學多於“說"科學，學生較少獲得交流與解釋的機會。, 其次PCK本身的程度影響課堂教學實踐的轉化。研究發現三位教師當中，有經驗教師的PCK各個知識成分比較均衡，知識成分之間能夠產生聯繫，PCK與教學行為之間的差異較小。新手教師的PCK發展處於不均衡狀態，其中教學目標和評價知識較為豐富，但是缺乏充分的教學策略知識來實現教學目標的轉變。PCK不僅僅是知識成分的綜合，它體現了教師將不同知識整合的能力，有經驗教師的整合能力明顯高於新手教師。此外，學生知識是變化最為劇烈的PCK知識成分，教師需要特別的提示或是刺激才能促進其在教學計劃中更多地考慮學生。, 最後，教師面對探究教學的實施總體呈現一種複雜而矛盾的信念。這背後的影響因素主要來自五個方面：一是教學觀念，例如教師對學習“過程"和“結果"的價值判斷，通常“結果"定律影響探究教學的實施；二是自我效能感，自我效能感高的教師更能實現教學轉化；三是學生觀念，教師對學生的評價越是負面，越會阻礙教學轉化；四是同伴學習，擁有同儕支持的教師能夠獲得更多的教學資源以及自我效能感，如果有優秀教師的引領，這種自我效能感將更加得到強化；五是教科書、課程標準、考試等外在因素，通常“課程"和“考試"是教師認為最容易阻礙探究教學實施的兩大外部壓力。, 基於以上發現，研究建議值得繼續關注的問題是：進一步確定PCK的評級方法和工具，幫助教師形成均衡發展的PCK；促進教師深入理解和反思探究的本質；為教師提供支持性的環境，包括穩定的培訓環境、增加教師之間學習的機會、支持教師對自我教學進行不斷的改進和跟新、鼓勵教師形成積極、正面、陽關的教學心態。研究對於教師專業發展和提高科學本質觀的認識這兩方面具有一定的理論和實踐貢獻。, The notion of pedagogical content knowledge (PCK) was proposed in the 1980s. PCK is closely related to teachers’ classroom practices, but a review of research on PCK revealed that few previous studies had focused on how PCK is transformed into classroom practice. Using three high school chemistry teachers in Beijing as cases, this study investigated the transformation process of PCK. They taught chemical reaction rate by using inquiry teaching and learning in their schools. Interviews and direct observations were used to collect data on the actual teaching and learning process in their classrooms. The research focused on four areas: teacher knowledge and beliefs about inquiry; the PCK for inquiry teaching; teacher behaviors in the classroom; and the transformation of PCK into classroom teaching as well as the factors affecting the transformation process., It was found that the process of PCK transformation can be analyzed from three perspectives. First, teachers’ levels of understanding of inquiry affected their selection of learning objectives, content, teaching strategies, and assessment. Three major difficulties encountered by the three teachers were identified. Secondly, teachers’ levels of PCK influenced the transformation of PCK into classroom teaching. Experienced teachers were able to transform their PCK more easily than novice teachers. However, both experienced and novice teachers had to pay more attention to students’ needs when designing and implementing inquiry teaching. Thirdly, the three teachers held complex and conflicting beliefs about teaching and learning. The key factors affecting the transformation of PCK into classroom teaching included teacher self-efficacy, beliefs about student ability, peer support, textbooks, curriculum guides, and examinations., These findings have important implications for teacher professional development and science teaching and learning in school., Detailed summary in vernacular field only., Detailed summary in vernacular field only., Detailed summary in vernacular field only., Detailed summary in vernacular field only., Detailed summary in vernacular field only., 廖梁., Thesis (Ph.D.)--Chinese University of Hong Kong, 2012., Includes bibliographical references (leaves 331-350)., Electronic reproduction. Hong Kong : Chinese University of Hong Kong, [2012] System requirements: Adobe Acrobat Reader. Available via World Wide Web., s in Chinese and English., Liao Liang., 摘要 --- p.iii, p.v, 致謝 --- p.v, 目錄 --- p.ix, 圖表目錄 --- p.xii, Chapter 第一章 --- 引言 --- p.1, Chapter 第一節 --- 研究背景 --- p.1, Chapter 一、 --- 學科教學知識研究概述 --- p.1, Chapter 二、 --- 課程改革與探究教學 --- p.3, Chapter 第二節 --- 研究目的 --- p.6, Chapter 一、 --- 內容主題+探究取向的PCK研究 --- p.6, Chapter 二、 --- 教師的探究知識和信念 --- p.7, Chapter 三、 --- PCK在課堂實踐中的轉化過程 --- p.8, Chapter 第三節、 --- 研究問題 --- p.9, Chapter 第二章 --- 文獻回顧 --- p.11, Chapter 第一節 --- PCK的概念与成分 --- p.11, Chapter 一、 --- 概念與內涵 --- p.11, Chapter 二、 --- 知識成分 --- p.17, Chapter 第二節、 --- 主題式PCK --- p.31, Chapter 一、 --- 概述 --- p.31, Chapter 二、 --- Van Driel的主題PCK研究----教師的化學平衡PCK及其發展 --- p.33, Chapter 三、 --- De Jong等人的主題PCK研究---教師有關粒子模型的PCK --- p.34, Chapter 四、 --- Drechsler&Van Driel的主題PCK研究 --- p.36, Chapter 五、 --- 小結 --- p.37, Chapter 第三節、 --- PCK的發展與課堂教學實踐 --- p.39, Chapter 一、 --- Cochran的PCK發展觀---“動態建構與“均衡發展 --- p.39, Chapter 二、 --- Nilsson的PCK發展觀---在反思中促進PCK的發展 --- p.41, Chapter 三、 --- Park&Oliver的PCK發展觀---PCK產生於行動，指導於行動 --- p.42, Chapter 四、 --- 小结 --- p.44, Chapter 第四節、 --- 獲得、描述和評價教師PCK的方法 --- p.45, Chapter 一、 --- 早期PCK研究方法（1986-1999） --- p.45, Chapter 二、 --- 2000---至今的PCK研究 --- p.47, Chapter 三、 --- 如何描述和呈現PCK --- p.49, Chapter 四、 --- 小結 --- p.53, Chapter 第五節、 --- 探究、探究教学与信念 --- p.54, Chapter 一、 --- 什麼是探究 --- p.54, Chapter 二、 --- 探究教學策略 --- p.60, Chapter 三、 --- 探究信念 --- p.67, Chapter 第六節、 --- 化學反應速率教學背景 --- p.70, Chapter 一、 --- 化學反應速率的概念要點 --- p.70, Chapter 二、 --- 學習化學反應速率常見的困難和錯誤概念 --- p.71, Chapter 三、 --- 化學反應速率的教學策略 --- p.72, Chapter 第三章 --- 研究方法 --- p.75, Chapter 第一節、 --- 案例研究方法概述 --- p.75, Chapter 第二節、 --- 資料收集 --- p.76, Chapter 一、 --- 第一次田野調查設計與初步結果 --- p.76, Chapter 二、 --- 第二次田野調查數據收集 --- p.81, Chapter 第三節、 --- 資料分析 --- p.88, Chapter 第四節、 --- 研究效度與研究倫理 --- p.91, Chapter 第四章 --- 教師的探究知識與信念 --- p.93, Chapter 第一節、 --- 教师的探究知識 --- p.94, Chapter 一、 --- 內涵 --- p.94, Chapter 二、 --- 過程 --- p.99, Chapter 三、 --- 角色 --- p.103, Chapter 四、 --- 價值 --- p.107, Chapter 五、 --- 困難 --- p.113, Chapter 第二節、 --- 教師對探究教學所持有的信念 --- p.117, Chapter 一、 --- 認同亦或疏離 --- p.120, Chapter 二、 --- 行动亦或观望 --- p.123, Chapter 三、 --- 堅持亦或嘗試 --- p.126, Chapter 四、 --- 融洽亦或矛盾 --- p.128, Chapter 第三節、 --- 小結 --- p.132, Chapter 第五章 --- 以探究為取向的學科教學知識分析 --- p.139, Chapter 第一節、 --- 學科教學知識分析框架 --- p.139, Chapter 第二節、 --- 理論先行，實驗輔助----喬老師的探究教學PCK --- p.146, Chapter 第三節、 --- 在教中學，吐故納新----郎老師學科教學知識分析 --- p.169, Chapter 第四節、 --- 適應困境，力圖改變----胡老師學科教學知識分析 --- p.182, Chapter 第五節、 --- 小结 --- p.197, Chapter 第六章 --- 課堂教學行為分析 --- p.203, Chapter 第一節、 --- 探究課堂教學中的師生對話分析框架 --- p.204, Chapter 第二節、 --- 喬老師的課堂教學行為分析 --- p.206, Chapter 第三節、 --- 郎老師師生課堂對話分析 --- p.241, Chapter 第四節、 --- 胡老師師生課堂對話分析 --- p.251, Chapter 第五節、 --- 小結 --- p.262, Chapter 第七章 --- 學科教學知識向課堂實踐轉化过程的討論 --- p.268, Chapter 第一節、 --- 學科教學知識與課堂教學行為差異討論 --- p.268, Chapter 一、 --- 教學目標與教學行為 --- p.268, Chapter 二、 --- 教學內容與教學行為 --- p.274, Chapter 三、 --- 教學策略與教學行為 --- p.276, Chapter 四、 --- 教學評價與教學行為 --- p.282, Chapter 五、 --- 小結 --- p.286, Chapter 第二節、 --- 學科教學知識向教學行為轉化過程的特徵 --- p.287, Chapter 一、 --- 喬老師的轉化特徵----深刻的認識，深刻的矛盾 --- p.288, Chapter 二、 --- 郎老師教學知識的轉化特徵----知識與行動的高度一致 --- p.294, Chapter 三、 --- 胡老師教學知識的轉化特徵----艱難融入教學環境，信念頑強 --- p.298, Chapter 第三節、 --- 轉化的影響因素討論 --- p.302, Chapter 一、 --- 探究知識對轉化的影響 --- p.302, Chapter 二、 --- 信念對轉化的影響 --- p.307, Chapter 三、 --- PCK對轉化的影響 --- p.312, Chapter 第八章 --- 結論與總結 --- p.316, Chapter 第一節、 --- 結論 --- p.316, Chapter 第二節、 --- 研究貢獻 --- p.321, Chapter 第三節、 --- 研究局限 --- p.325, Chapter 第四節、 --- 有待深入關注的問題 --- p.327, 參考文獻 --- p.331, 中文部分 --- p.331, 英文部分 --- p.333, 附錄 --- p.351, http://library.cuhk.edu.hk/record=b5549376, Use of this resource is governed by the terms and conditions of the Creative Commons “Attribution-NonCommercial-NoDerivatives 4.0 International” License (http://creativecommons.org/licenses/by-nc-nd/4.0/)