Search

Rapid advancements have been made in extending Large Language Models (LLMs) to Large Multi-modal Models (LMMs). However, extending input modality of LLMs to video data remains a challenging endeavor, especially for long videos. Due to insufficient access to large-scale high-quality video data and the excessive compression of visual features, current methods exhibit limitations in effectively processing long videos. In this paper, we introduce Kangaroo, a powerful Video LMM aimed at addressing these challenges. Confronted with issue of inadequate training data, we develop a data curation system to build a large-scale dataset with high-quality annotations for vision-language pre-training and instruction tuning. In addition, we design a curriculum training pipeline with gradually increasing resolution and number of input frames to accommodate long videos. Evaluation results demonstrate that, with 8B parameters, Kangaroo achieves state-of-the-art performance across a variety of video understanding benchmarks while exhibiting competitive results on others. Particularly, on benchmarks specialized for long videos, Kangaroo excels some larger models with over 10B parameters and proprietary models.

Real-world navigation often involves dealing with unexpected obstructions such as closed doors, moved objects, and unpredictable entities. However, mainstream Vision-and-Language Navigation (VLN) tasks typically assume instructions perfectly align with the fixed and predefined navigation graphs without any obstructions. This assumption overlooks potential discrepancies in actual navigation graphs and given instructions, which can cause major failures for both indoor and outdoor agents. To address this issue, we integrate diverse obstructions into the R2R dataset by modifying both the navigation graphs and visual observations, introducing an innovative dataset and task, R2R with UNexpected Obstructions (R2R-UNO). R2R-UNO contains various types and numbers of path obstructions to generate instruction-reality mismatches for VLN research. Experiments on R2R-UNO reveal that state-of-the-art VLN methods inevitably encounter significant challenges when facing such mismatches, indicating that they rigidly follow instructions rather than navigate adaptively. Therefore, we propose a novel method called ObVLN (Obstructed VLN), which includes a curriculum training strategy and virtual graph construction to help agents effectively adapt to obstructed environments. Empirical results show that ObVLN not only maintains robust performance in unobstructed scenarios but also achieves a substantial performance advantage with unexpected obstructions., Comment: Accepted to MM 2024

Offline reinforcement learning (RL) is an effective tool for real-world recommender systems with its capacity to model the dynamic interest of users and its interactive nature. Most existing offline RL recommender systems focus on model-based RL through learning a world model from offline data and building the recommendation policy by interacting with this model. Although these methods have made progress in the recommendation performance, the effectiveness of model-based offline RL methods is often constrained by the accuracy of the estimation of the reward model and the model uncertainties, primarily due to the extreme discrepancy between offline logged data and real-world data in user interactions with online platforms. To fill this gap, a more accurate reward model and uncertainty estimation are needed for the model-based RL methods. In this paper, a novel model-based Reward Shaping in Offline Reinforcement Learning for Recommender Systems, ROLeR, is proposed for reward and uncertainty estimation in recommendation systems. Specifically, a non-parametric reward shaping method is designed to refine the reward model. In addition, a flexible and more representative uncertainty penalty is designed to fit the needs of recommendation systems. Extensive experiments conducted on four benchmark datasets showcase that ROLeR achieves state-of-the-art performance compared with existing baselines. The source code can be downloaded at https://github.com/ArronDZhang/ROLeR., Comment: CIKM 2024

Recently, various pre-trained language models (PLMs) have been proposed to prove their impressive performances on a wide range of few-shot tasks. However, limited by the unstructured prior knowledge in PLMs, it is difficult to maintain consistent performance on complex structured scenarios, such as hierarchical text classification (HTC), especially when the downstream data is extremely scarce. The main challenge is how to transfer the unstructured semantic space in PLMs to the downstream domain hierarchy. Unlike previous work on HTC which directly performs multi-label classification or uses graph neural network (GNN) to inject label hierarchy, in this work, we study the HTC problem under a few-shot setting to adapt knowledge in PLMs from an unstructured manner to the downstream hierarchy. Technically, we design a simple yet effective method named Hierarchical Iterative Conditional Random Field (HierICRF) to search the most domain-challenging directions and exquisitely crafts domain-hierarchy adaptation as a hierarchical iterative language modeling problem, and then it encourages the model to make hierarchical consistency self-correction during the inference, thereby achieving knowledge transfer with hierarchical consistency preservation. We perform HierICRF on various architectures, and extensive experiments on two popular HTC datasets demonstrate that prompt with HierICRF significantly boosts the few-shot HTC performance with an average Micro-F1 by 28.80% to 1.50% and Macro-F1 by 36.29% to 1.5% over the previous state-of-the-art (SOTA) baselines under few-shot settings, while remaining SOTA hierarchical consistency performance., Comment: 9 pages, 2 figures, Accepted by IJCAI2024

Continual Knowledge Graph Embedding (CKGE) aims to efficiently learn new knowledge and simultaneously preserve old knowledge. Dominant approaches primarily focus on alleviating catastrophic forgetting of old knowledge but neglect efficient learning for the emergence of new knowledge. However, in real-world scenarios, knowledge graphs (KGs) are continuously growing, which brings a significant challenge to fine-tuning KGE models efficiently. To address this issue, we propose a fast CKGE framework (\model), incorporating an incremental low-rank adapter (\mec) mechanism to efficiently acquire new knowledge while preserving old knowledge. Specifically, to mitigate catastrophic forgetting, \model\ isolates and allocates new knowledge to specific layers based on the fine-grained influence between old and new KGs. Subsequently, to accelerate fine-tuning, \model\ devises an efficient \mec\ mechanism, which embeds the specific layers into incremental low-rank adapters with fewer training parameters. Moreover, \mec\ introduces adaptive rank allocation, which makes the LoRA aware of the importance of entities and adjusts its rank scale adaptively. We conduct experiments on four public datasets and two new datasets with a larger initial scale. Experimental results demonstrate that \model\ can reduce training time by 34\%-49\% while still achieving competitive link prediction performance against state-of-the-art models on four public datasets (average MRR score of 21.0\% vs. 21.1\%).Meanwhile, on two newly constructed datasets, \model\ saves 51\%-68\% training time and improves link prediction performance by 1.5\%., Comment: Accepted by IJCAI2024

Current Vision-and-Language Navigation (VLN) tasks mainly employ textual instructions to guide agents. However, being inherently abstract, the same textual instruction can be associated with different visual signals, causing severe ambiguity and limiting the transfer of prior knowledge in the vision domain from the user to the agent. To fill this gap, we propose Vision-and-Language Navigation with Multi-modal Prompts (VLN-MP), a novel task augmenting traditional VLN by integrating both natural language and images in instructions. VLN-MP not only maintains backward compatibility by effectively handling text-only prompts but also consistently shows advantages with different quantities and relevance of visual prompts. Possible forms of visual prompts include both exact and similar object images, providing adaptability and versatility in diverse navigation scenarios. To evaluate VLN-MP under a unified framework, we implement a new benchmark that offers: (1) a training-free pipeline to transform textual instructions into multi-modal forms with landmark images; (2) diverse datasets with multi-modal instructions for different downstream tasks; (3) a novel module designed to process various image prompts for seamless integration with state-of-the-art VLN models. Extensive experiments on four VLN benchmarks (R2R, RxR, REVERIE, CVDN) show that incorporating visual prompts significantly boosts navigation performance. While maintaining efficiency with text-only prompts, VLN-MP enables agents to navigate in the pre-explore setting and outperform text-based models, showing its broader applicability., Comment: IJCAI 2024

Coherent elastic neutrino-nucleus scattering (CEvNS) provides a unique probe for neutrino properties Beyond the Standard Model (BSM) physics. REactor neutrino LIquid xenon Coherent Scattering experiment (RELICS), a proposed reactor neutrino program using liquid xenon time projection chamber (LXeTPC) technology, aims to investigate the CEvNS process of antineutrinos off xenon atomic nuclei. In this work, the design of the experiment is studied and optimized based on Monte Carlo (MC) simulations. To achieve a sufficiently low energy threshold for CEvNS detection, an ionization-only analysis channel is adopted for RELICS. A high emission rate of delayed electrons after a big ionization signal is the major background, leading to an analysis threshold of 120 photo-electrons in the CEvNS search. The second largest background, nuclear recoils induced by cosmic-ray neutrons, is suppressed via a passive water shield. The physics potential of RELICS is explored with a 32 kg-yr exposure at a baseline of 25 m from a reactor core with a 3 GW thermal power. In an energy range of 120 to 240 PE, we expect 4902.4 CEvNS and 1318.4 background events. The sensitivity of RELICS to the weak mixing angle is investigated at a low momentum transfer. Our study shows that RELICS can further improve the constraints on the non-standard neutrino interaction (NSI) compared to the current best results.

Traditional knowledge graph embedding (KGE) methods typically require preserving the entire knowledge graph (KG) with significant training costs when new knowledge emerges. To address this issue, the continual knowledge graph embedding (CKGE) task has been proposed to train the KGE model by learning emerging knowledge efficiently while simultaneously preserving decent old knowledge. However, the explicit graph structure in KGs, which is critical for the above goal, has been heavily ignored by existing CKGE methods. On the one hand, existing methods usually learn new triples in a random order, destroying the inner structure of new KGs. On the other hand, old triples are preserved with equal priority, failing to alleviate catastrophic forgetting effectively. In this paper, we propose a competitive method for CKGE based on incremental distillation (IncDE), which considers the full use of the explicit graph structure in KGs. First, to optimize the learning order, we introduce a hierarchical strategy, ranking new triples for layer-by-layer learning. By employing the inter- and intra-hierarchical orders together, new triples are grouped into layers based on the graph structure features. Secondly, to preserve the old knowledge effectively, we devise a novel incremental distillation mechanism, which facilitates the seamless transfer of entity representations from the previous layer to the next one, promoting old knowledge preservation. Finally, we adopt a two-stage training paradigm to avoid the over-corruption of old knowledge influenced by under-trained new knowledge. Experimental results demonstrate the superiority of IncDE over state-of-the-art baselines. Notably, the incremental distillation mechanism contributes to improvements of 0.2%-6.5% in the mean reciprocal rank (MRR) score., Comment: Accepted by AAAI 2024

Relation extraction (RE) aims to identify relations between entities mentioned in texts. Although large language models (LLMs) have demonstrated impressive in-context learning (ICL) abilities in various tasks, they still suffer from poor performances compared to most supervised fine-tuned RE methods. Utilizing ICL for RE with LLMs encounters two challenges: (1) retrieving good demonstrations from training examples, and (2) enabling LLMs exhibit strong ICL abilities in RE. On the one hand, retrieving good demonstrations is a non-trivial process in RE, which easily results in low relevance regarding entities and relations. On the other hand, ICL with an LLM achieves poor performance in RE while RE is different from language modeling in nature or the LLM is not large enough. In this work, we propose a novel recall-retrieve-reason RE framework that synergizes LLMs with retrieval corpora (training examples) to enable relevant retrieving and reliable in-context reasoning. Specifically, we distill the consistently ontological knowledge from training datasets to let LLMs generate relevant entity pairs grounded by retrieval corpora as valid queries. These entity pairs are then used to retrieve relevant training examples from the retrieval corpora as demonstrations for LLMs to conduct better ICL via instruction tuning. Extensive experiments on different LLMs and RE datasets demonstrate that our method generates relevant and valid entity pairs and boosts ICL abilities of LLMs, achieving competitive or new state-of-the-art performance on sentence-level RE compared to previous supervised fine-tuning methods and ICL-based methods., Comment: IJCAI 2024

Relation extraction (RE) is an important task that aims to identify the relationships between entities in texts. While large language models (LLMs) have revealed remarkable in-context learning (ICL) capability for general zero and few-shot learning, recent studies indicate that current LLMs still struggle with zero and few-shot RE. Previous studies are mainly dedicated to design prompt formats and select good examples for improving ICL-based RE. Although both factors are vital for ICL, if one can fundamentally boost the ICL capability of LLMs in RE, the zero and few-shot RE performance via ICL would be significantly improved. To this end, we introduce \textsc{Micre} (\textbf{M}eta \textbf{I}n-\textbf{C}ontext learning of LLMs for \textbf{R}elation \textbf{E}xtraction), a new meta-training framework for zero and few-shot RE where an LLM is tuned to do ICL on a diverse collection of RE datasets (i.e., learning to learn in context for RE). Through meta-training, the model becomes more effectively to learn a new RE task in context by conditioning on a few training examples with no parameter updates or task-specific templates at inference time, enabling better zero and few-shot task generalization. We experiment \textsc{Micre} on various LLMs with different model scales and 12 public RE datasets, and then evaluate it on unseen RE benchmarks under zero and few-shot settings. \textsc{Micre} delivers comparable or superior performance compared to a range of baselines including supervised fine-tuning and typical in-context learning methods. We find that the gains are particular significant for larger model scales, and using a diverse set of the meta-training RE datasets is key to improvements. Empirically, we show that \textsc{Micre} can transfer the relation semantic knowledge via relation label name during inference on target RE datasets., Comment: IJCAI 2024

Dialogue relation extraction (DRE) aims to extract relations between two arguments within a dialogue, which is more challenging than standard RE due to the higher person pronoun frequency and lower information density in dialogues. However, existing DRE methods still suffer from two serious issues: (1) hard to capture long and sparse multi-turn information, and (2) struggle to extract golden relations based on partial dialogues, which motivates us to discover more effective methods that can alleviate the above issues. We notice that the rise of large language models (LLMs) has sparked considerable interest in evaluating their performance across diverse tasks. To this end, we initially investigate the capabilities of different LLMs in DRE, considering both proprietary models and open-source models. Interestingly, we discover that LLMs significantly alleviate two issues in existing DRE methods. Generally, we have following findings: (1) scaling up model size substantially boosts the overall DRE performance and achieves exceptional results, tackling the difficulty of capturing long and sparse multi-turn information; (2) LLMs encounter with much smaller performance drop from entire dialogue setting to partial dialogue setting compared to existing methods; (3) LLMs deliver competitive or superior performances under both full-shot and few-shot settings compared to current state-of-the-art; (4) LLMs show modest performances on inverse relations but much stronger improvements on general relations, and they can handle dialogues of various lengths especially for longer sequences., Comment: IJCAI 2024

Background: Liver tumors are abnormal growths in the liver that can be either benign or malignant, with liver cancer being a significant health concern worldwide. However, there is no dataset for plain scan segmentation of liver tumors, nor any related algorithms. To fill this gap, we propose Plain Scan Liver Tumors(PSLT) and YNetr. Methods: A collection of 40 liver tumor plain scan segmentation datasets was assembled and annotated. Concurrently, we utilized Dice coefficient as the metric for assessing the segmentation outcomes produced by YNetr, having advantage of capturing different frequency information. Results: The YNetr model achieved a Dice coefficient of 62.63% on the PSLT dataset, surpassing the other publicly available model by an accuracy margin of 1.22%. Comparative evaluations were conducted against a range of models including UNet 3+, XNet, UNetr, Swin UNetr, Trans-BTS, COTr, nnUNetv2 (2D), nnUNetv2 (3D fullres), MedNext (2D) and MedNext(3D fullres). Conclusions: We not only proposed a dataset named PSLT(Plain Scan Liver Tumors), but also explored a structure called YNetr that utilizes wavelet transform to extract different frequency information, which having the SOTA in PSLT by experiments., Comment: My academic research interests have undergone significant changes. I believe that continuing to retain the paper is no longer in line with my academic development path, and may also mislead readers. And some of the content may involve the boundaries of personal privacy. To respect and protect the privacy of relevant personnel, I decided to withdraw it to avoid any unnecessary controversy or harm

The in-context learning (ICL) for relational triple extraction (RTE) has achieved promising performance, but still encounters two key challenges: (1) how to design effective prompts and (2) how to select proper demonstrations. Existing methods, however, fail to address these challenges appropriately. On the one hand, they usually recast RTE task to text-to-text prompting formats, which is unnatural and results in a mismatch between the output format at the pre-training time and the inference time for large language models (LLMs). On the other hand, they only utilize surface natural language features and lack consideration of triple semantics in sample selection. These issues are blocking improved performance in ICL for RTE, thus we aim to tackle prompt designing and sample selection challenges simultaneously. To this end, we devise a tabular prompting for RTE (\textsc{TableIE}) which frames RTE task into a table generation task to incorporate explicit structured information into ICL, facilitating conversion of outputs to RTE structures. Then we propose instructive in-context learning (I$^2$CL) which only selects and annotates a few samples considering internal triple semantics in massive unlabeled samples., Comment: LREC-COLING 2024

Many existing coverless steganography methods establish a mapping relationship between cover images and hidden data. There exists an issue that the number of images stored in the database grows exponentially as the steganographic capacity rises. The need for a high steganographic capacity makes it challenging to build an image database. To improve the image library utilization and anti-attack capability of the steganography system, we present an efficient coverless scheme based on dynamically matched substrings. YOLO is employed for selecting optimal objects, and a mapping dictionary is established between these objects and scrambling factors. With the aid of this dictionary, each image is effectively assigned to a specific scrambling factor, which is used to scramble the receiver's sequence key. To achieve sufficient steganography capability based on a limited image library, all substrings of the scrambled sequences hold the potential to hide data. After completing the secret information matching, the ideal number of stego images will be obtained from the database. According to experimental results, this technology outperforms most previous works on data load, transmission security, and hiding capacity. Under typical geometric attacks, it can recover 79.85\% of secret information on average. Furthermore, only approximately 200 random images are needed to meet a capacity of 19 bits per image.

In recent years, the recognition of free-hand sketches has remained a popular task. However, in some special fields such as the military field, free-hand sketches are difficult to sample on a large scale. Common data augmentation and image generation techniques are difficult to produce images with various free-hand sketching styles. Therefore, the recognition and segmentation tasks in related fields are limited. In this paper, we propose a novel adversarial generative network that can accurately generate realistic free-hand sketches with various styles. We explore the performance of the model, including using styles randomly sampled from a prior normal distribution to generate images with various free-hand sketching styles, disentangling the painters' styles from known free-hand sketches to generate images with specific styles, and generating images of unknown classes that are not in the training set. We further demonstrate with qualitative and quantitative evaluations our advantages in visual quality, content accuracy, and style imitation on SketchIME., Comment: 6 pages, 7 figures, ICSMD

In this paper, we explore a principal way to enhance the quality of object masks produced by different segmentation models. We propose a model-agnostic solution called SegRefiner, which offers a novel perspective on this problem by interpreting segmentation refinement as a data generation process. As a result, the refinement process can be smoothly implemented through a series of denoising diffusion steps. Specifically, SegRefiner takes coarse masks as inputs and refines them using a discrete diffusion process. By predicting the label and corresponding states-transition probabilities for each pixel, SegRefiner progressively refines the noisy masks in a conditional denoising manner. To assess the effectiveness of SegRefiner, we conduct comprehensive experiments on various segmentation tasks, including semantic segmentation, instance segmentation, and dichotomous image segmentation. The results demonstrate the superiority of our SegRefiner from multiple aspects. Firstly, it consistently improves both the segmentation metrics and boundary metrics across different types of coarse masks. Secondly, it outperforms previous model-agnostic refinement methods by a significant margin. Lastly, it exhibits a strong capability to capture extremely fine details when refining high-resolution images. The source code and trained models are available at https://github.com/MengyuWang826/SegRefiner., Comment: NeurIPS 2023, Code: https://github.com/MengyuWang826/SegRefiner

Vision Transformers (ViTs) have revolutionized the field of computer vision, yet their deployments on resource-constrained devices remain challenging due to high computational demands. To expedite pre-trained ViTs, token pruning and token merging approaches have been developed, which aim at reducing the number of tokens involved in the computation. However, these methods still have some limitations, such as image information loss from pruned tokens and inefficiency in the token-matching process. In this paper, we introduce a novel Graph-based Token Propagation (GTP) method to resolve the challenge of balancing model efficiency and information preservation for efficient ViTs. Inspired by graph summarization algorithms, GTP meticulously propagates less significant tokens' information to spatially and semantically connected tokens that are of greater importance. Consequently, the remaining few tokens serve as a summarization of the entire token graph, allowing the method to reduce computational complexity while preserving essential information of eliminated tokens. Combined with an innovative token selection strategy, GTP can efficiently identify image tokens to be propagated. Extensive experiments have validated GTP's effectiveness, demonstrating both efficiency and performance improvements. Specifically, GTP decreases the computational complexity of both DeiT-S and DeiT-B by up to 26% with only a minimal 0.3% accuracy drop on ImageNet-1K without finetuning, and remarkably surpasses the state-of-the-art token merging method on various backbones at an even faster inference speed. The source code is available at https://github.com/Ackesnal/GTP-ViT., Comment: Accepted to WACV2024 (Oral)

Conventionally, during the knowledge distillation process (e.g. feature distillation), an additional projector is often required to perform feature transformation due to the dimension mismatch between the teacher and the student networks. Interestingly, we discovered that even if the student and the teacher have the same feature dimensions, adding a projector still helps to improve the distillation performance. In addition, projectors even improve logit distillation if we add them to the architecture too. Inspired by these surprising findings and the general lack of understanding of the projectors in the knowledge distillation process from existing literature, this paper investigates the implicit role that projectors play but so far have been overlooked. Our empirical study shows that the student with a projector (1) obtains a better trade-off between the training accuracy and the testing accuracy compared to the student without a projector when it has the same feature dimensions as the teacher, (2) better preserves its similarity to the teacher beyond shallow and numeric resemblance, from the view of Centered Kernel Alignment (CKA), and (3) avoids being over-confident as the teacher does at the testing phase. Motivated by the positive effects of projectors, we propose a projector ensemble-based feature distillation method to further improve distillation performance. Despite the simplicity of the proposed strategy, empirical results from the evaluation of classification tasks on benchmark datasets demonstrate the superior classification performance of our method on a broad range of teacher-student pairs and verify from the aspects of CKA and model calibration that the student's features are of improved quality with the projector ensemble design., Comment: arXiv admin note: text overlap with arXiv:2210.15274

Vision Transformers (ViTs) have demonstrated outstanding performance in computer vision tasks, yet their high computational complexity prevents their deployment in computing resource-constrained environments. Various token pruning techniques have been introduced to alleviate the high computational burden of ViTs by dynamically dropping image tokens. However, some undesirable pruning at early stages may result in permanent loss of image information in subsequent layers, consequently hindering model performance. To address this problem, we propose IdleViT, a dynamic token-idle-based method that achieves an excellent trade-off between performance and efficiency. Specifically, in each layer, IdleViT selects a subset of the image tokens to participate in computations while keeping the rest of the tokens idle and directly passing them to this layer's output. By allowing the idle tokens to be re-selected in the following layers, IdleViT mitigates the negative impact of improper pruning in the early stages. Furthermore, inspired by the normalized graph cut, we devise a token cut loss on the attention map as regularization to improve IdleViT's token selection ability. Our method is simple yet effective and can be extended to pyramid ViTs since no token is completely dropped. Extensive experimental results on various ViT architectures have shown that IdleViT can diminish the complexity of pretrained ViTs by up to 33\% with no more than 0.2\% accuracy decrease on ImageNet, after finetuning for only 30 epochs. Notably, when the keep ratio is 0.5, IdleViT outperforms the state-of-the-art EViT on DeiT-S by 0.5\% higher accuracy and even faster inference speed. The source code is available in the supplementary material., Comment: Accepted to AJCAI2023

Vision Transformers (ViTs) have demonstrated remarkable performance in various computer vision tasks. However, the high computational complexity hinders ViTs' applicability on devices with limited memory and computing resources. Although certain investigations have delved into the fusion of convolutional layers with self-attention mechanisms to enhance the efficiency of ViTs, there remains a knowledge gap in constructing tiny yet effective ViTs solely based on the self-attention mechanism. Furthermore, the straightforward strategy of reducing the feature channels in a large but outperforming ViT often results in significant performance degradation despite improved efficiency. To address these challenges, we propose a novel channel shuffle module to improve tiny-size ViTs, showing the potential of pure self-attention models in environments with constrained computing resources. Inspired by the channel shuffle design in ShuffleNetV2 \cite{ma2018shufflenet}, our module expands the feature channels of a tiny ViT and partitions the channels into two groups: the \textit{Attended} and \textit{Idle} groups. Self-attention computations are exclusively employed on the designated \textit{Attended} group, followed by a channel shuffle operation that facilitates information exchange between the two groups. By incorporating our module into a tiny ViT, we can achieve superior performance while maintaining a comparable computational complexity to the vanilla model. Specifically, our proposed channel shuffle module consistently improves the top-1 accuracy on the ImageNet-1K dataset for various tiny ViT models by up to 2.8\%, with the changes in model complexity being less than 0.03 GMACs.

Regulatory compliance auditing across diverse industrial domains requires heightened quality assurance and traceability. Present manual and intermittent approaches to such auditing yield significant challenges, potentially leading to oversights in the monitoring process. To address these issues, we introduce a real-time, multi-modal sensing system employing 3D time-of-flight and RGB cameras, coupled with unsupervised learning techniques on edge AI devices. This enables continuous object tracking thereby enhancing efficiency in record-keeping and minimizing manual interventions. While we validate the system in a knife sanitization context within agrifood facilities, emphasizing its prowess against occlusion and low-light issues with RGB cameras, its potential spans various industrial monitoring settings.

Current video object detection (VOD) models often encounter issues with over-aggregation due to redundant aggregation strategies, which perform feature aggregation on every frame. This results in suboptimal performance and increased computational complexity. In this work, we propose an image-level Object Detection Difficulty (ODD) metric to quantify the difficulty of detecting objects in a given image. The derived ODD scores can be used in the VOD process to mitigate over-aggregation. Specifically, we train an ODD predictor as an auxiliary head of a still-image object detector to compute the ODD score for each image based on the discrepancies between detection results and ground-truth bounding boxes. The ODD score enhances the VOD system in two ways: 1) it enables the VOD system to select superior global reference frames, thereby improving overall accuracy; and 2) it serves as an indicator in the newly designed ODD Scheduler to eliminate the aggregation of frames that are easy to detect, thus accelerating the VOD process. Comprehensive experiments demonstrate that, when utilized for selecting global reference frames, ODD-VOD consistently enhances the accuracy of Global-frame-based VOD models. When employed for acceleration, ODD-VOD consistently improves the frames per second (FPS) by an average of 73.3% across 8 different VOD models without sacrificing accuracy. When combined, ODD-VOD attains state-of-the-art performance when competing with many VOD methods in both accuracy and speed. Our work represents a significant advancement towards making VOD more practical for real-world applications., Comment: 11 pages, 6 figures, accepted by ACM MM2023

Hand Pose Estimation (HPE) is crucial to many applications, but conventional cameras-based CM-HPE methods are completely subject to Line-of-Sight (LoS), as cameras cannot capture occluded objects. In this paper, we propose to exploit Radio-Frequency-Vision (RF-vision) capable of bypassing obstacles for achieving occluded HPE, and we introduce OCHID-Fi as the first RF-HPE method with 3D pose estimation capability. OCHID-Fi employs wideband RF sensors widely available on smart devices (e.g., iPhones) to probe 3D human hand pose and extract their skeletons behind obstacles. To overcome the challenge in labeling RF imaging given its human incomprehensible nature, OCHID-Fi employs a cross-modality and cross-domain training process. It uses a pre-trained CM-HPE network and a synchronized CM/RF dataset, to guide the training of its complex-valued RF-HPE network under LoS conditions. It further transfers knowledge learned from labeled LoS domain to unlabeled occluded domain via adversarial learning, enabling OCHID-Fi to generalize to unseen occluded scenarios. Experimental results demonstrate the superiority of OCHID-Fi: it achieves comparable accuracy to CM-HPE under normal conditions while maintaining such accuracy even in occluded scenarios, with empirical evidence for its generalizability to new domains., Comment: Accepted to ICCV 2023

Vision transformers have achieved leading performance on various visual tasks yet still suffer from high computational complexity. The situation deteriorates in dense prediction tasks like semantic segmentation, as high-resolution inputs and outputs usually imply more tokens involved in computations. Directly removing the less attentive tokens has been discussed for the image classification task but can not be extended to semantic segmentation since a dense prediction is required for every patch. To this end, this work introduces a Dynamic Token Pruning (DToP) method based on the early exit of tokens for semantic segmentation. Motivated by the coarse-to-fine segmentation process by humans, we naturally split the widely adopted auxiliary-loss-based network architecture into several stages, where each auxiliary block grades every token's difficulty level. We can finalize the prediction of easy tokens in advance without completing the entire forward pass. Moreover, we keep $k$ highest confidence tokens for each semantic category to uphold the representative context information. Thus, computational complexity will change with the difficulty of the input, akin to the way humans do segmentation. Experiments suggest that the proposed DToP architecture reduces on average $20\% - 35\%$ of computational cost for current semantic segmentation methods based on plain vision transformers without accuracy degradation.

Real-world graphs, such as social networks, financial transactions, and recommendation systems, often demonstrate dynamic behavior. This phenomenon, known as graph stream, involves the dynamic changes of nodes and the emergence and disappearance of edges. To effectively capture both the structural and temporal aspects of these dynamic graphs, dynamic graph neural networks have been developed. However, existing methods are usually tailored to process either continuous-time or discrete-time dynamic graphs, and cannot be generalized from one to the other. In this paper, we propose a decoupled graph neural network for large dynamic graphs, including a unified dynamic propagation that supports efficient computation for both continuous and discrete dynamic graphs. Since graph structure-related computations are only performed during the propagation process, the prediction process for the downstream task can be trained separately without expensive graph computations, and therefore any sequence model can be plugged-in and used. As a result, our algorithm achieves exceptional scalability and expressiveness. We evaluate our algorithm on seven real-world datasets of both continuous-time and discrete-time dynamic graphs. The experimental results demonstrate that our algorithm achieves state-of-the-art performance in both kinds of dynamic graphs. Most notably, the scalability of our algorithm is well illustrated by its successful application to large graphs with up to over a billion temporal edges and over a hundred million nodes.

Recent advancements in pre-trained vision-language models, such as CLIP, have enabled the segmentation of arbitrary concepts solely from textual inputs, a process commonly referred to as open-vocabulary semantic segmentation (OVS). However, existing OVS techniques confront a fundamental challenge: the trained classifier tends to overfit on the base classes observed during training, resulting in suboptimal generalization performance to unseen classes. To mitigate this issue, recent studies have proposed the use of an additional frozen pre-trained CLIP for classification. Nonetheless, this approach incurs heavy computational overheads as the CLIP vision encoder must be repeatedly forward-passed for each mask, rendering it impractical for real-world applications. To address this challenge, our objective is to develop a fast OVS model that can perform comparably or better without the extra computational burden of the CLIP image encoder during inference. To this end, we propose a core idea of preserving the generalizable representation when fine-tuning on known classes. Specifically, we introduce a text diversification strategy that generates a set of synonyms for each training category, which prevents the learned representation from collapsing onto specific known category names. Additionally, we employ a text-guided knowledge distillation method to preserve the generalizable knowledge of CLIP. Extensive experiments demonstrate that our proposed model achieves robust generalization performance across various datasets. Furthermore, we perform a preliminary exploration of open-vocabulary video segmentation and present a benchmark that can facilitate future open-vocabulary research in the video domain., Comment: Accepted by ICCV2023

Object classification using LiDAR 3D point cloud data is critical for modern applications such as autonomous driving. However, labeling point cloud data is labor-intensive as it requires human annotators to visualize and inspect the 3D data from different perspectives. In this paper, we propose a semi-supervised cross-domain learning approach that does not rely on manual annotations of point clouds and performs similar to fully-supervised approaches. We utilize available 3D object models to train classifiers that can generalize to real-world point clouds. We simulate the acquisition of point clouds by sampling 3D object models from multiple viewpoints and with arbitrary partial occlusions. We then augment the resulting set of point clouds through random rotations and adding Gaussian noise to better emulate the real-world scenarios. We then train point cloud encoding models, e.g., DGCNN, PointNet++, on the synthesized and augmented datasets and evaluate their cross-domain classification performance on corresponding real-world datasets. We also introduce Point-Syn2Real, a new benchmark dataset for cross-domain learning on point clouds. The results of our extensive experiments with this dataset demonstrate that the proposed cross-domain learning approach for point clouds outperforms the related baseline and state-of-the-art approaches in both indoor and outdoor settings in terms of cross-domain generalizability. The code and data will be available upon publishing.

In knowledge distillation, previous feature distillation methods mainly focus on the design of loss functions and the selection of the distilled layers, while the effect of the feature projector between the student and the teacher remains under-explored. In this paper, we first discuss a plausible mechanism of the projector with empirical evidence and then propose a new feature distillation method based on a projector ensemble for further performance improvement. We observe that the student network benefits from a projector even if the feature dimensions of the student and the teacher are the same. Training a student backbone without a projector can be considered as a multi-task learning process, namely achieving discriminative feature extraction for classification and feature matching between the student and the teacher for distillation at the same time. We hypothesize and empirically verify that without a projector, the student network tends to overfit the teacher's feature distributions despite having different architecture and weights initialization. This leads to degradation on the quality of the student's deep features that are eventually used in classification. Adding a projector, on the other hand, disentangles the two learning tasks and helps the student network to focus better on the main feature extraction task while still being able to utilize teacher features as a guidance through the projector. Motivated by the positive effect of the projector in feature distillation, we propose an ensemble of projectors to further improve the quality of student features. Experimental results on different datasets with a series of teacher-student pairs illustrate the effectiveness of the proposed method., Comment: NeurIPS 2022

We propose a video feature representation learning framework called STAR-GNN, which applies a pluggable graph neural network component on a multi-scale lattice feature graph. The essence of STAR-GNN is to exploit both the temporal dynamics and spatial contents as well as visual connections between regions at different scales in the frames. It models a video with a lattice feature graph in which the nodes represent regions of different granularity, with weighted edges that represent the spatial and temporal links. The contextual nodes are aggregated simultaneously by graph neural networks with parameters trained with retrieval triplet loss. In the experiments, we show that STAR-GNN effectively implements a dynamic attention mechanism on video frame sequences, resulting in the emphasis for dynamic and semantically rich content in the video, and is robust to noise and redundancies. Empirical results show that STAR-GNN achieves state-of-the-art performance for Content-Based Video Retrieval., Comment: 6 pages, 2 figures, ICME 2022 accepted paper

After a survey for person-tracking system-induced privacy concerns, we propose a black-box adversarial attack method on state-of-the-art human detection models called InvisibiliTee. The method learns printable adversarial patterns for T-shirts that cloak wearers in the physical world in front of person-tracking systems. We design an angle-agnostic learning scheme which utilizes segmentation of the fashion dataset and a geometric warping process so the adversarial patterns generated are effective in fooling person detectors from all camera angles and for unseen black-box detection models. Empirical results in both digital and physical environments show that with the InvisibiliTee on, person-tracking systems' ability to detect the wearer drops significantly., Comment: 12 pages, 10 figures and the ICANN 2022 accpeted paper