Search

Owing to the ubiquity and easy-to-shape property of optical intensity, the intensity gradient force of light has been most spectacularly exploited in optical manipulation of small particles. Manifesting the intensity gradient as an optical torque to spin particles is of great fascination on both fundamental and practical sides but remains elusive. Here, we uncover the existence of the optical intensity-gradient torque in the interaction of light with chiral particles. Such a new type of torque derives from the interplay between chirality induced multipoles, which switches its direction for particles with opposite chirality. We show that this torque can be directly detected by a simple standing wave field, created with the interference of two counterpropagating plane-like waves. Our work offers a unique route to achieve rotational control of matter by tailoring the field intensity of Maxwell waves. It also establishes a framework that maps a remarkable connection among the optical forces and torques, across chiral to nonchiral.

Embodied agents require robust navigation systems to operate in unstructured environments, making the robustness of Simultaneous Localization and Mapping (SLAM) models critical to embodied agent autonomy. While real-world datasets are invaluable, simulation-based benchmarks offer a scalable approach for robustness evaluations. However, the creation of a challenging and controllable noisy world with diverse perturbations remains under-explored. To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations. The pipeline comprises a comprehensive taxonomy of sensor and motion perturbations for embodied multi-modal (specifically RGB-D) sensing, categorized by their sources and propagation order, allowing for procedural composition. We also provide a toolbox for synthesizing these perturbations, enabling the transformation of clean environments into challenging noisy simulations. Utilizing the pipeline, we instantiate the large-scale Noisy-Replica benchmark, which includes diverse perturbation types, to evaluate the risk tolerance of existing advanced RGB-D SLAM models. Our extensive analysis uncovers the susceptibilities of both neural (NeRF and Gaussian Splatting -based) and non-neural SLAM models to disturbances, despite their demonstrated accuracy in standard benchmarks. Our code is publicly available at https://github.com/Xiaohao-Xu/SLAM-under-Perturbation., Comment: 50 pages. arXiv admin note: substantial text overlap with arXiv:2402.08125

Towards open-ended Video Anomaly Detection (VAD), existing methods often exhibit biased detection when faced with challenging or unseen events and lack interpretability. To address these drawbacks, we propose Holmes-VAD, a novel framework that leverages precise temporal supervision and rich multimodal instructions to enable accurate anomaly localization and comprehensive explanations. Firstly, towards unbiased and explainable VAD system, we construct the first large-scale multimodal VAD instruction-tuning benchmark, i.e., VAD-Instruct50k. This dataset is created using a carefully designed semi-automatic labeling paradigm. Efficient single-frame annotations are applied to the collected untrimmed videos, which are then synthesized into high-quality analyses of both abnormal and normal video clips using a robust off-the-shelf video captioner and a large language model (LLM). Building upon the VAD-Instruct50k dataset, we develop a customized solution for interpretable video anomaly detection. We train a lightweight temporal sampler to select frames with high anomaly response and fine-tune a multimodal large language model (LLM) to generate explanatory content. Extensive experimental results validate the generality and interpretability of the proposed Holmes-VAD, establishing it as a novel interpretable technique for real-world video anomaly analysis. To support the community, our benchmark and model will be publicly available at https://holmesvad.github.io., Comment: 19 pages, 9 figures

This paper presents LogiCode, a novel framework that leverages Large Language Models (LLMs) for identifying logical anomalies in industrial settings, moving beyond traditional focus on structural inconsistencies. By harnessing LLMs for logical reasoning, LogiCode autonomously generates Python codes to pinpoint anomalies such as incorrect component quantities or missing elements, marking a significant leap forward in anomaly detection technologies. A custom dataset "LOCO-Annotations" and a benchmark "LogiBench" are introduced to evaluate the LogiCode's performance across various metrics including binary classification accuracy, code generation success rate, and precision in reasoning. Findings demonstrate LogiCode's enhanced interpretability, significantly improving the accuracy of logical anomaly detection and offering detailed explanations for identified anomalies. This represents a notable shift towards more intelligent, LLM-driven approaches in industrial anomaly detection, promising substantial impacts on industry-specific applications.

In autonomous driving, multi-modal perception models leveraging inputs from multiple sensors exhibit strong robustness in degraded environments. However, these models face challenges in efficiently and effectively transferring learned representations across different modalities and tasks. This paper presents NeRF-Supervised Masked Auto Encoder (NS-MAE), a self-supervised pre-training paradigm for transferable multi-modal representation learning. NS-MAE is designed to provide pre-trained model initializations for efficient and high-performance fine-tuning. Our approach uses masked multi-modal reconstruction in neural radiance fields (NeRF), training the model to reconstruct missing or corrupted input data across multiple modalities. Specifically, multi-modal embeddings are extracted from corrupted LiDAR point clouds and images, conditioned on specific view directions and locations. These embeddings are then rendered into projected multi-modal feature maps using neural rendering techniques. The original multi-modal signals serve as reconstruction targets for the rendered feature maps, facilitating self-supervised representation learning. Extensive experiments demonstrate the promising transferability of NS-MAE representations across diverse multi-modal and single-modal perception models. This transferability is evaluated on various 3D perception downstream tasks, such as 3D object detection and BEV map segmentation, using different amounts of fine-tuning labeled data. Our code will be released to support the community., Comment: 8 pages. arXiv admin note: substantial text overlap with arXiv:2311.13750

The robustness of driving perception systems under unprecedented conditions is crucial for safety-critical usages. Latest advancements have prompted increasing interests towards multi-LiDAR perception. However, prevailing driving datasets predominantly utilize single-LiDAR systems and collect data devoid of adverse conditions, failing to capture the complexities of real-world environments accurately. Addressing these gaps, we proposed Place3D, a full-cycle pipeline that encompasses LiDAR placement optimization, data generation, and downstream evaluations. Our framework makes three appealing contributions. 1) To identify the most effective configurations for multi-LiDAR systems, we introduce a Surrogate Metric of the Semantic Occupancy Grids (M-SOG) to evaluate LiDAR placement quality. 2) Leveraging the M-SOG metric, we propose a novel optimization strategy to refine multi-LiDAR placements. 3) Centered around the theme of multi-condition multi-LiDAR perception, we collect a 364,000-frame dataset from both clean and adverse conditions. Extensive experiments demonstrate that LiDAR placements optimized using our approach outperform various baselines. We showcase exceptional robustness in both 3D object detection and LiDAR semantic segmentation tasks, under diverse adverse weather and sensor failure conditions. Code and benchmark toolkit are publicly available., Comment: Preprint; 40 pages, 11 figures, 15 tables; Code at https://github.com/ywyeli/Place3D

Anomaly detection is vital in various industrial scenarios, including the identification of unusual patterns in production lines and the detection of manufacturing defects for quality control. Existing techniques tend to be specialized in individual scenarios and lack generalization capacities. In this study, we aim to develop a generic anomaly detection model applicable across multiple scenarios. To achieve this, we customize generic visual-language foundation models that possess extensive knowledge and robust reasoning abilities into anomaly detectors and reasoners. Specifically, we introduce a multi-modal prompting strategy that incorporates domain knowledge from experts as conditions to guide the models. Our approach considers multi-modal prompt types, including task descriptions, class context, normality rules, and reference images. In addition, we unify the input representation of multi-modality into a 2D image format, enabling multi-modal anomaly detection and reasoning. Our preliminary studies demonstrate that combining visual and language prompts as conditions for customizing the models enhances anomaly detection performance. The customized models showcase the ability to detect anomalies across different data modalities such as images and point clouds. Qualitative case studies further highlight the anomaly detection and reasoning capabilities, particularly for multi-object scenes and temporal data. Our code is available at https://github.com/Xiaohao-Xu/Customizable-VLM.

In recent years, video anomaly detection has been extensively investigated in both unsupervised and weakly supervised settings to alleviate costly temporal labeling. Despite significant progress, these methods still suffer from unsatisfactory results such as numerous false alarms, primarily due to the absence of precise temporal anomaly annotation. In this paper, we present a novel labeling paradigm, termed "glance annotation", to achieve a better balance between anomaly detection accuracy and annotation cost. Specifically, glance annotation is a random frame within each abnormal event, which can be easily accessed and is cost-effective. To assess its effectiveness, we manually annotate the glance annotations for two standard video anomaly detection datasets: UCF-Crime and XD-Violence. Additionally, we propose a customized GlanceVAD method, that leverages gaussian kernels as the basic unit to compose the temporal anomaly distribution, enabling the learning of diverse and robust anomaly representations from the glance annotations. Through comprehensive analysis and experiments, we verify that the proposed labeling paradigm can achieve an excellent trade-off between annotation cost and model performance. Extensive experimental results also demonstrate the effectiveness of our GlanceVAD approach, which significantly outperforms existing advanced unsupervised and weakly supervised methods. Code and annotations will be publicly available at https://github.com/pipixin321/GlanceVAD., Comment: 21 pages

Referring perception, which aims at grounding visual objects with multimodal referring guidance, is essential for bridging the gap between humans, who provide instructions, and the environment where intelligent systems perceive. Despite progress in this field, the robustness of referring perception models (RPMs) against disruptive perturbations is not well explored. This work thoroughly assesses the resilience of RPMs against various perturbations in both general and specific contexts. Recognizing the complex nature of referring perception tasks, we present a comprehensive taxonomy of perturbations, and then develop a versatile toolbox for synthesizing and evaluating the effects of composite disturbances. Employing this toolbox, we construct $\text{R}^2$-Bench, a benchmark for assessing the Robustness of Referring perception models under noisy conditions across five key tasks. Moreover, we propose the $\text{R}^2$-Agent, an LLM-based agent that simplifies and automates model evaluation via natural language instructions. Our investigation uncovers the vulnerabilities of current RPMs to various perturbations and provides tools for assessing model robustness, potentially promoting the safe and resilient integration of intelligent systems into complex real-world scenarios., Comment: Code and dataset will be released at https://github.com/lxa9867/r2bench

Robustness is a crucial factor for the successful deployment of robots in unstructured environments, particularly in the domain of Simultaneous Localization and Mapping (SLAM). Simulation-based benchmarks have emerged as a highly scalable approach for robustness evaluation compared to real-world data collection. However, crafting a challenging and controllable noisy world with diverse perturbations remains relatively under-explored. To this end, we propose a novel, customizable pipeline for noisy data synthesis, aimed at assessing the resilience of multi-modal SLAM models against various perturbations. This pipeline incorporates customizable hardware setups, software components, and perturbed environments. In particular, we introduce comprehensive perturbation taxonomy along with a perturbation composition toolbox, allowing the transformation of clean simulations into challenging noisy environments. Utilizing the pipeline, we instantiate the Robust-SLAM benchmark, which includes diverse perturbation types, to evaluate the risk tolerance of existing advanced multi-modal SLAM models. Our extensive analysis uncovers the susceptibilities of existing SLAM models to real-world disturbance, despite their demonstrated accuracy in standard benchmarks. Our perturbation synthesis toolbox, SLAM robustness evaluation pipeline, and Robust-SLAM benchmark will be made publicly available at https://github.com/Xiaohao-Xu/SLAM-under-Perturbation/., Comment: 40 pages

Visual Anomaly Detection (VAD) endeavors to pinpoint deviations from the concept of normality in visual data, widely applied across diverse domains, e.g., industrial defect inspection, and medical lesion detection. This survey comprehensively examines recent advancements in VAD by identifying three primary challenges: 1) scarcity of training data, 2) diversity of visual modalities, and 3) complexity of hierarchical anomalies. Starting with a brief overview of the VAD background and its generic concept definitions, we progressively categorize, emphasize, and discuss the latest VAD progress from the perspective of sample number, data modality, and anomaly hierarchy. Through an in-depth analysis of the VAD field, we finally summarize future developments for VAD and conclude the key findings and contributions of this survey., Comment: Work in progress. Yunkang Cao, Xiaohao Xu, and Jiangning Zhang contribute equally to this work

This work proposes a unified self-supervised pre-training framework for transferable multi-modal perception representation learning via masked multi-modal reconstruction in Neural Radiance Field (NeRF), namely NeRF-Supervised Masked AutoEncoder (NS-MAE). Specifically, conditioned on certain view directions and locations, multi-modal embeddings extracted from corrupted multi-modal input signals, i.e., Lidar point clouds and images, are rendered into projected multi-modal feature maps via neural rendering. Then, original multi-modal signals serve as reconstruction targets for the rendered multi-modal feature maps to enable self-supervised representation learning. Extensive experiments show that the representation learned via NS-MAE shows promising transferability for diverse multi-modal and single-modal (camera-only and Lidar-only) perception models on diverse 3D perception downstream tasks (3D object detection and BEV map segmentation) with diverse amounts of fine-tuning labeled data. Moreover, we empirically find that NS-MAE enjoys the synergy of both the mechanism of masked autoencoder and neural radiance field. We hope this study can inspire exploration of more general multi-modal representation learning for autonomous agents.

Anomaly detection is a crucial task across different domains and data types. However, existing anomaly detection models are often designed for specific domains and modalities. This study explores the use of GPT-4V(ision), a powerful visual-linguistic model, to address anomaly detection tasks in a generic manner. We investigate the application of GPT-4V in multi-modality, multi-domain anomaly detection tasks, including image, video, point cloud, and time series data, across multiple application areas, such as industrial, medical, logical, video, 3D anomaly detection, and localization tasks. To enhance GPT-4V's performance, we incorporate different kinds of additional cues such as class information, human expertise, and reference images as prompts.Based on our experiments, GPT-4V proves to be highly effective in detecting and explaining global and fine-grained semantic patterns in zero/one-shot anomaly detection. This enables accurate differentiation between normal and abnormal instances. Although we conducted extensive evaluations in this study, there is still room for future evaluation to further exploit GPT-4V's generic anomaly detection capacity from different aspects. These include exploring quantitative metrics, expanding evaluation benchmarks, incorporating multi-round interactions, and incorporating human feedback loops. Nevertheless, GPT-4V exhibits promising performance in generic anomaly detection and understanding, thus opening up a new avenue for anomaly detection., Comment: Work in progress. Evaluated GPT-4V on 4 modalities, 9 tasks, and 15 datasets. The first three authors contribute equally

Cameras and LiDARs are both important sensors for autonomous driving, playing critical roles in 3D object detection. Camera-LiDAR Fusion has been a prevalent solution for robust and accurate driving perception. In contrast to the vast majority of existing arts that focus on how to improve the performance of 3D target detection through cross-modal schemes, deep learning algorithms, and training tricks, we devote attention to the impact of sensor configurations on the performance of learning-based methods. To achieve this, we propose a unified information-theoretic surrogate metric for camera and LiDAR evaluation based on the proposed sensor perception model. We also design an accelerated high-quality framework for data acquisition, model training, and performance evaluation that functions with the CARLA simulator. To show the correlation between detection performance and our surrogate metrics, We conduct experiments using several camera-LiDAR placements and parameters inspired by self-driving companies and research institutions. Extensive experimental results of representative algorithms on nuScenes dataset validate the effectiveness of our surrogate metric, demonstrating that sensor configurations significantly impact point-cloud-image fusion based detection models, which contribute up to 30% discrepancy in terms of the average precision.

Audiovisual segmentation (AVS) is a challenging task that aims to segment visual objects in videos according to their associated acoustic cues. With multiple sound sources and background disturbances involved, establishing robust correspondences between audio and visual contents poses unique challenges due to (1) complex entanglement across sound sources and (2) frequent changes in the occurrence of distinct sound events. Assuming sound events occur independently, the multi-source semantic space can be represented as the Cartesian product of single-source sub-spaces. We are motivated to decompose the multi-source audio semantics into single-source semantics for more effective interactions with visual content. We propose a semantic decomposition method based on product quantization, where the multi-source semantics can be decomposed and represented by several disentangled and noise-suppressed single-source semantics. Furthermore, we introduce a global-to-local quantization mechanism, which distills knowledge from stable global (clip-level) features into local (frame-level) ones, to handle frequent changes in audio semantics. Extensive experiments demonstrate that our semantically decomposed audio representation significantly improves AVS performance, e.g., +21.2% mIoU on the challenging AVS-Semantic benchmark with ResNet50 backbone. https://github.com/lxa9867/QSD.

Panoramic videos contain richer spatial information and have attracted tremendous amounts of attention due to their exceptional experience in some fields such as autonomous driving and virtual reality. However, existing datasets for video segmentation only focus on conventional planar images. To address the challenge, in this paper, we present a panoramic video dataset, PanoVOS. The dataset provides 150 videos with high video resolutions and diverse motions. To quantify the domain gap between 2D planar videos and panoramic videos, we evaluate 15 off-the-shelf video object segmentation (VOS) models on PanoVOS. Through error analysis, we found that all of them fail to tackle pixel-level content discontinues of panoramic videos. Thus, we present a Panoramic Space Consistency Transformer (PSCFormer), which can effectively utilize the semantic boundary information of the previous frame for pixel-level matching with the current frame. Extensive experiments demonstrate that compared with the previous SOTA models, our PSCFormer network exhibits a great advantage in terms of segmentation results under the panoramic setting. Our dataset poses new challenges in panoramic VOS and we hope that our PanoVOS can advance the development of panoramic segmentation/tracking., Comment: ECCV 2024

Point-supervised Temporal Action Localization (PSTAL) is an emerging research direction for label-efficient learning. However, current methods mainly focus on optimizing the network either at the snippet-level or the instance-level, neglecting the inherent reliability of point annotations at both levels. In this paper, we propose a Hierarchical Reliability Propagation (HR-Pro) framework, which consists of two reliability-aware stages: Snippet-level Discrimination Learning and Instance-level Completeness Learning, both stages explore the efficient propagation of high-confidence cues in point annotations. For snippet-level learning, we introduce an online-updated memory to store reliable snippet prototypes for each class. We then employ a Reliability-aware Attention Block to capture both intra-video and inter-video dependencies of snippets, resulting in more discriminative and robust snippet representation. For instance-level learning, we propose a point-based proposal generation approach as a means of connecting snippets and instances, which produces high-confidence proposals for further optimization at the instance level. Through multi-level reliability-aware learning, we obtain more reliable confidence scores and more accurate temporal boundaries of predicted proposals. Our HR-Pro achieves state-of-the-art performance on multiple challenging benchmarks, including an impressive average mAP of 60.3% on THUMOS14. Notably, our HR-Pro largely surpasses all previous point-supervised methods, and even outperforms several competitive fully supervised methods. Code will be available at https://github.com/pipixin321/HR-Pro., Comment: Accepted by AAAI24

This technical report introduces the winning solution of the team Segment Any Anomaly for the CVPR2023 Visual Anomaly and Novelty Detection (VAND) challenge. Going beyond uni-modal prompt, e.g., language prompt, we present a novel framework, i.e., Segment Any Anomaly + (SAA$+$), for zero-shot anomaly segmentation with multi-modal prompts for the regularization of cascaded modern foundation models. Inspired by the great zero-shot generalization ability of foundation models like Segment Anything, we first explore their assembly (SAA) to leverage diverse multi-modal prior knowledge for anomaly localization. Subsequently, we further introduce multimodal prompts (SAA$+$) derived from domain expert knowledge and target image context to enable the non-parameter adaptation of foundation models to anomaly segmentation. The proposed SAA$+$ model achieves state-of-the-art performance on several anomaly segmentation benchmarks, including VisA and MVTec-AD, in the zero-shot setting. We will release the code of our winning solution for the CVPR2023 VAN., Comment: The first two author contribute equally. CVPR workshop challenge report. arXiv admin note: substantial text overlap with arXiv:2305.10724

We present a novel framework, i.e., Segment Any Anomaly + (SAA+), for zero-shot anomaly segmentation with hybrid prompt regularization to improve the adaptability of modern foundation models. Existing anomaly segmentation models typically rely on domain-specific fine-tuning, limiting their generalization across countless anomaly patterns. In this work, inspired by the great zero-shot generalization ability of foundation models like Segment Anything, we first explore their assembly to leverage diverse multi-modal prior knowledge for anomaly localization. For non-parameter foundation model adaptation to anomaly segmentation, we further introduce hybrid prompts derived from domain expert knowledge and target image context as regularization. Our proposed SAA+ model achieves state-of-the-art performance on several anomaly segmentation benchmarks, including VisA, MVTec-AD, MTD, and KSDD2, in the zero-shot setting. We will release the code at \href{https://github.com/caoyunkang/Segment-Any-Anomaly}{https://github.com/caoyunkang/Segment-Any-Anomaly}., Comment: The first two authors contribute equally. The code will be available on https://github.com/caoyunkang/Segment-Any-Anomaly

Point cloud (PCD) anomaly detection steadily emerges as a promising research area. This study aims to improve PCD anomaly detection performance by combining handcrafted PCD descriptions with powerful pre-trained 2D neural networks. To this end, this study proposes Complementary Pseudo Multimodal Feature (CPMF) that incorporates local geometrical information in 3D modality using handcrafted PCD descriptors and global semantic information in the generated pseudo 2D modality using pre-trained 2D neural networks. For global semantics extraction, CPMF projects the origin PCD into a pseudo 2D modality containing multi-view images. These images are delivered to pre-trained 2D neural networks for informative 2D modality feature extraction. The 3D and 2D modality features are aggregated to obtain the CPMF for PCD anomaly detection. Extensive experiments demonstrate the complementary capacity between 2D and 3D modality features and the effectiveness of CPMF, with 95.15% image-level AU-ROC and 92.93% pixel-level PRO on the MVTec3D benchmark. Code is available on https://github.com/caoyunkang/CPMF., Comment: Submitted to Pattern Recognition. Code is available on https://github.com/caoyunkang/CPMF

Most unsupervised image anomaly localization methods suffer from overgeneralization because of the high generalization abilities of convolutional neural networks, leading to unreliable predictions. To mitigate the overgeneralization, this study proposes to collaboratively optimize normal and abnormal feature distributions with the assistance of synthetic anomalies, namely collaborative discrepancy optimization (CDO). CDO introduces a margin optimization module and an overlap optimization module to optimize the two key factors determining the localization performance, i.e., the margin and the overlap between the discrepancy distributions (DDs) of normal and abnormal samples. With CDO, a large margin and a small overlap between normal and abnormal DDs are obtained, and the prediction reliability is boosted. Experiments on MVTec2D and MVTec3D show that CDO effectively mitigates the overgeneralization and achieves great anomaly localization performance with real-time computation efficiency. A real-world automotive plastic parts inspection application further demonstrates the capability of the proposed CDO. Code is available on https://github.com/caoyunkang/CDO., Comment: Accepted by IEEE Transactions on Industrial Informatics

The momentum carried by structured light fields exhibits a rich array of surprising features. In this work, we generate transverse orbital angular momentum (TOAM) in the interference field of two parallel and counterpropagating linearly-polarised focused beams, synthesising an array of identical handedness vortices carrying intrinsic TOAM. We explore this structured light field using an optomechanical sensor, consisting of an optically levitated silicon nanorod, whose rotation is a probe of the optical angular momentum, which generates an exceptionally large torque. This simple creation and direct observation of TOAM will have applications in studies of fundamental physics, the optical manipulation of matter and quantum optomechanics.

How to design an optimal wearable device for human movement recognition is vital to reliable and accurate human-machine collaboration. Previous works mainly fabricate wearable devices heuristically. Instead, this paper raises an academic question: can we design an optimization algorithm to optimize the fabrication of wearable devices such as figuring out the best sensor arrangement automatically? Specifically, this work focuses on optimizing the placement of Forcemyography (FMG) sensors for FMG armbands in the application of arm movement recognition. Firstly, based on graph theory, the armband is modeled considering sensors' signals and connectivity. Then, a Graph-based Armband Modeling Network (GAM-Net) is introduced for arm movement recognition. Afterward, the sensor placement optimization for FMG armbands is formulated and an optimization algorithm with greedy local search is proposed. To study the effectiveness of our optimization algorithm, a dataset for mechanical maintenance tasks using FMG armbands with 16 sensors is collected. Our experiments show that using only 4 sensors optimized with our algorithm can help maintain a comparable recognition accuracy to using all sensors. Finally, the optimized sensor placement result is verified from a physiological view. This work would like to shed light on the automatic fabrication of wearable devices considering downstream tasks, such as human biological signal collection and movement recognition. Our code and dataset are available at https://github.com/JerryX1110/IROS22-FMG-Sensor-Optimization, Comment: 6 pages, 10 figures, Accepted by IROS22 (The 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

Video instance segmentation (VIS) aims at classifying, segmenting and tracking object instances in video sequences. Recent transformer-based neural networks have demonstrated their powerful capability of modeling spatio-temporal correlations for the VIS task. Relying on video- or clip-level input, they suffer from high latency and computational cost. We propose a robust context fusion network to tackle VIS in an online fashion, which predicts instance segmentation frame-by-frame with a few preceding frames. To acquire the precise and temporal-consistent prediction for each frame efficiently, the key idea is to fuse effective and compact context from reference frames into the target frame. Considering the different effects of reference and target frames on the target prediction, we first summarize contextual features through importance-aware compression. A transformer encoder is adopted to fuse the compressed context. Then, we leverage an order-preserving instance embedding to convey the identity-aware information and correspond the identities to predicted instance masks. We demonstrate that our robust fusion network achieves the best performance among existing online VIS methods and is even better than previously published clip-level methods on the Youtube-VIS 2019 and 2021 benchmarks. In addition, visual objects often have acoustic signatures that are naturally synchronized with them in audio-bearing video recordings. By leveraging the flexibility of our context fusion network on multi-modal data, we further investigate the influence of audios on the video-dense prediction task, which has never been discussed in existing works. We build up an Audio-Visual Instance Segmentation dataset, and demonstrate that acoustic signals in the wild scenarios could benefit the VIS task.

Referring Video Object Segmentation (R-VOS) is a challenging task that aims to segment an object in a video based on a linguistic expression. Most existing R-VOS methods have a critical assumption: the object referred to must appear in the video. This assumption, which we refer to as semantic consensus, is often violated in real-world scenarios, where the expression may be queried against false videos. In this work, we highlight the need for a robust R-VOS model that can handle semantic mismatches. Accordingly, we propose an extended task called Robust R-VOS, which accepts unpaired video-text inputs. We tackle this problem by jointly modeling the primary R-VOS problem and its dual (text reconstruction). A structural text-to-text cycle constraint is introduced to discriminate semantic consensus between video-text pairs and impose it in positive pairs, thereby achieving multi-modal alignment from both positive and negative pairs. Our structural constraint effectively addresses the challenge posed by linguistic diversity, overcoming the limitations of previous methods that relied on the point-wise constraint. A new evaluation dataset, R\textsuperscript{2}-Youtube-VOSis constructed to measure the model robustness. Our model achieves state-of-the-art performance on R-VOS benchmarks, Ref-DAVIS17 and Ref-Youtube-VOS, and also our R\textsuperscript{2}-Youtube-VOS~dataset., Comment: iccv 2023, https://github.com/lxa9867/R2VOS

In the booming video era, video segmentation attracts increasing research attention in the multimedia community. Semi-supervised video object segmentation (VOS) aims at segmenting objects in all target frames of a video, given annotated object masks of reference frames. Most existing methods build pixel-wise reference-target correlations and then perform pixel-wise tracking to obtain target masks. Due to neglecting object-level cues, pixel-level approaches make the tracking vulnerable to perturbations, and even indiscriminate among similar objects. Towards robust VOS, the key insight is to calibrate the representation and mask of each specific object to be expressive and discriminative. Accordingly, we propose a new deep network, which can adaptively construct object representations and calibrate object masks to achieve stronger robustness. First, we construct the object representations by applying an adaptive object proxy (AOP) aggregation method, where the proxies represent arbitrary-shaped segments at multi-levels for reference. Then, prototype masks are initially generated from the reference-target correlations based on AOP. Afterwards, such proto-masks are further calibrated through network modulation, conditioning on the object proxy representations. We consolidate this conditional mask calibration process in a progressive manner, where the object representations and proto-masks evolve to be discriminative iteratively. Extensive experiments are conducted on the standard VOS benchmarks, YouTube-VOS-18/19 and DAVIS-17. Our model achieves the state-of-the-art performance among existing published works, and also exhibits superior robustness against perturbations. Our project repo is at https://github.com/JerryX1110/Robust-Video-Object-Segmentation, Comment: 19 pages, 17 figures, ACM Multimedia 2022 Accepted

The imaginary Poynting momentum (IPM) of light has been captivated an unusual origin of optomechanical effects on dipolar magnetoelectric particles, but yet observed in experiments. Here, we report, for the very first time, a whole family of high-order IPM forces for not only magnetoelectric but also generic Mie particles, assisted with their excited higher multipoles within. Such optomechanical phenomena derive from a nonlinear contribution of the IPM to the optical force, and can be remarkable even when the incident IPM is small. We observe the high-order optomechanics in a structured light beam with vortex-like IPM streamlines, which allows the low-order dipolar contribution to be suppressed. Our results provide the first unambiguous evidence of the ponderomotive nature of the IPM, expand the classification of optical forces and open new possibilities for optical forces and micromanipulations.

We uncover the existence of a universal phenomenon concerning the electromagnetic optical force exerted by light or other electromagnetic waves on a distribution of charges and currents in general, and of particles in particular. This conveys the appearence of underlying reactive quantities that hinder radiation pressure and currently observed time-averaged forces. This constitutes a novel paradigm of the mechanical efficiency of light on matter, and completes the landscape of the electromagnetic force in classical electrodynamics; widening our understanding in the design of both illumination and particles in optical manipulation without the need of increasing the illuminating power, and thus lowering dissipation and heating. We show that this may be accomplished through the minimization of what we establish as the reactive strength of canonical (i.e. orbital) momentum, which plays against the optical force a role analogous to that of the reactive power versus the radiation efficiency of an antenna. This long time overlooked quantity, important for current progress of optical manipulation, and that stems from the complex Maxwell theorem of conservation of complex momentum that we put forward, as well as its alternating flow associated to the imaginary part of the complex Maxwell stress tensor, conform the imaginary Lorentz force that we introduce in this work, and that like the reactive strength of orbital momentum, is antagonic to the well-known time-averaged force; thus making this reactive Lorentz force indirectly observable near wavelengths at which the time-averaged force is lowered.

Error propagation is a general but crucial problem in online semi-supervised video object segmentation. We aim to suppress error propagation through a correction mechanism with high reliability. The key insight is to disentangle the correction from the conventional mask propagation process with reliable cues. We introduce two modulators, propagation and correction modulators, to separately perform channel-wise re-calibration on the target frame embeddings according to local temporal correlations and reliable references respectively. Specifically, we assemble the modulators with a cascaded propagation-correction scheme. This avoids overriding the effects of the reliable correction modulator by the propagation modulator. Although the reference frame with the ground truth label provides reliable cues, it could be very different from the target frame and introduce uncertain or incomplete correlations. We augment the reference cues by supplementing reliable feature patches to a maintained pool, thus offering more comprehensive and expressive object representations to the modulators. In addition, a reliability filter is designed to retrieve reliable patches and pass them in subsequent frames. Our model achieves state-of-the-art performance on YouTube-VOS18/19 and DAVIS17-Val/Test benchmarks. Extensive experiments demonstrate that the correction mechanism provides considerable performance gain by fully utilizing reliable guidance. Code is available at: https://github.com/JerryX1110/RPCMVOS., Comment: 13 pages, 8 figures, AAAI 2022 Accepted

We put forward the complex helicity theorem. It constitutes a novel law that rules the build-up of the reactive helicity through its zero time-average flow. Its imaginary Poynting momentum accounts for the accretion of reactive power, are illustrated in: evanescent waves and fields scattered from magnetodielectric dipolar nanoparticles. As for the former, we show that its reactive helicity may be experimentally observed as we introduce a reactive spin momentum and a reactive orbital momentum in terms of which we express the imaginary field momentum, whose transversal component produces an optical force on a magnetoelectric particle that, as we illustrate, may surpass and can be discriminated from, the known force due to the so-called extraordinary momentum. We also uncover a non-conservative force on such a magnetoelectric particle, acting in the decay direction of the evanescent wave, and that may also be discriminated from the standard gradient force; thus making the reactive power of the wavefield also observable. Concerning the light scattered by magnetoelectric nanoparticles, we establish two optical theorems that govern the accretion of reactive helicity and reactive power on extinction of incident wave helicity and energy. Like a nule total -- internal plus external -- reactive power is at the root of a resonant scattered power, we show that a zero total reactive helicity underlies a resonant scattered helicity. The first Kerker condition, under which the particle becomes dual on illumination with circularly polarized light, we demonstrate to amount to a nule overall scattered reactive helicity. and emission. We discover a discriminatory property of the reactive helicity of chiral light incident on a chiral nanoparticle by excitation of the external reactive power. This for optical near-field enantiomeric separation, we call reactive dichroism., Comment: 24 pages, 6 figures, revision submitted to Phys. Rev. Res