Fine-grained semantic segmentation of transmission-corridor point clouds is fundamental for intelligent power-line inspection. However, current progress is limited by realistic data scarcity and the difficulty of modeling global corridor structure and local geometric details in long, heterogeneous scenes. Existing public datasets usually provide only a few coarse categories or short cropped scenes which overlook long-range structural dependencies, severe long-tail distributions, and subtle distinctions among safety-critical components. As a result, current methods are difficult to evaluate under realistic inspection settings, and their ability to preserve and integrate complementary global and local cues remains unclear. To address the above challenges, we introduce TowerDataset, a heterogeneous benchmark for transmission-corridor segmentation. TowerDataset contains 661 real-world scenes and about 2.466 billion points. It preserves long corridor extents, defines a fine-grained 22-class taxonomy, and provides standardized splits and evaluation protocols. In addition, we present a global-local fusion framework which preserves and fuses whole-scene and local-detail information. A whole-scene branch with NoCrop training and prototypical contrastive learning captures long-range topology and contextual dependencies. A block-wise local branch retains fine geometric structures. Both predictions are then fused and refined by geometric validation. This design allows the model to exploit both global relationships and local shape details when recognizing rare and confusing components. Experiments on TowerDataset and two public benchmarks demonstrate the challenge of the proposed benchmark and the robustness of our framework in real, complex, and heterogeneous transmission-corridor scenes. The dataset will be released soon at https://huggingface.co/datasets/tccx18/Towerdataset/tree/main.

Tracking Any Point (TAP) has emerged as a fundamental tool for video understanding. Current approaches adapt Vision Foundation Models (VFMs) like DINOv2 via offline finetuning or test-time optimization. However, these VFMs rely on static image pre-training, which is inherently sub-optimal for capturing dense temporal correspondence in videos. To address this, we propose Mask-to-Point (M2P) learning, which leverages rich video object segmentation (VOS) mask annotations to improve VFMs for dense point tracking. Our M2P introduces three new mask-based constraints for weakly-supervised representation learning. First, we propose a local structure consistency loss, which leverages Procrustes analysis to model the cohesive motion of points lying within a local structure, achieving more reliable point-to-point matching learning. Second, we propose a mask label consistency (MLC) loss, which enforces that sampled foreground points strictly match foreground regions across frames. The proposed MLC loss can be regarded as a regularization, which stabilizes training and prevents convergence to trivial solutions. Finally, mask boundary constrain is applied to explicitly supervise boundary points. We show that our weaklysupervised M2P models significantly outperform baseline VFMs with efficient training by using only 3.6K VOS training videos. Notably, M2P achieves 12.8

Semi-supervised crowd analysis is a prominent area of research, as unlabeled data are typically abundant and inexpensive to obtain. However, traditional point-based annotations constrain performance because individual regions are inherently ambiguous, and consequently, learning fine-grained structural semantics from sparse anno tations remains an unresolved challenge. In this paper, we first propose an Exclusion-Constrained Dual-Prompt SAM (EDP-SAM), based on our Nearest Neighbor Exclusion Circle (NNEC) constraint, to generate mask supervision for current datasets. With the aim of segmenting individuals in dense scenes, we then propose Exclusivity-Guided Mask Learning (XMask), which enforces spatial separation through a discriminative mask objective. Gaussian smoothing and a differentiable center sampling strategy are utilized to improve feature continuity and training stability. Building on XMask, we present a semi-supervised crowd counting framework that uses instance mask priors as pseudo-labels, which contain richer shape information than traditional point cues. Extensive experiments on the ShanghaiTech A, UCF-QNRF, and JHU++ datasets (using 5

Multi-view crowd tracking estimates each person's tracking trajectories on the ground of the scene. Recent research works mainly rely on CNNs-based multi-view crowd tracking architectures, and most of them are evaluated and compared on relatively small datasets, such as Wildtrack and MultiviewX. Since these two datasets are collected in small scenes and only contain tens of frames in the evaluation stage, it is difficult for the current methods to be applied to real-world applications where scene size and occlusion are more complicated. In this paper, we propose a Transformer-based multi-view crowd tracking model, MVTrackTrans, which adopts interactions between camera views and the ground plane for enhanced multi-view tracking performance. Besides, for better evaluation, we collect and label two large real-world multi-view tracking datasets, MVCrowdTrack and CityTrack, which contain a much larger scene size over a longer time period. Compared with existing methods on the two large and new datasets, the proposed MVTrackTrans model achieves better performance, demonstrating the advantages of the model design in dealing with large scenes. We believe the proposed datasets and model will push the frontiers of the task to more practical scenarios, and the datasets and code will be made public upon paper acceptance.

Significant progress has been made in the improvement and downstream applications of the Contrastive Language-Image Pre-training (CLIP) vision-language model, while less attention has been paid to the interpretation of CLIP. We propose a Gradient-based visual and textual Explanation method for CLIP (Grad-ECLIP), which interprets the matching result of CLIP for a specific input image-text pair. By decomposing the encoder’s architecture and identifying the relationship between matching similarity and intermediate spatial features, Grad-ECLIP generates effective heat maps that reveal the impact of image regions or words on the CLIP results. Unlike previous Transformer interpretation methods that focus on utilizing self-attention maps, which are typically extremely sparse in CLIP, we produce high-quality visual explanations by applying channel and spatial weights to token features. Qualitative and quantitative evaluations verify the effectiveness and superiority of Grad-ECLIP compared with the state-of-the-art methods. Finally, a series of analyses are conducted based on our visual and textual explanation results, from which we explore the working mechanism of image-text matching, the strengths and limitations in attribution identification of CLIP, and the relationship between the concreteness/abstractness of a word and its usage in CLIP. The code of Grad-ECLIP is available here: https://github.com/Cyang-Zhao/Grad-Eclip.

Large Language Models (LLMs) are increasingly evaluated with input attribution methods, yet comparing such explanations remains challenging. Existing soft-perturbation faithfulness metrics, such as Soft-NC and Soft-NS, can conflate attribution quality with the number of words retained during perturbation: attribution methods with larger average scores may keep more words and therefore obtain inflated scores. To address this issue, we propose π-Soft-NC and π-Soft-NS, an evaluation framework that compares attribution methods under the same expected retaining probability, thus controlling the number of retained words. We further introduce Grad-ELLM, a gradient-based attribution method tailored to autoregressive decoder-only LLMs, which combines gradient-derived channel importance with attention-derived token importance at each decoding step. Experiments on classification and open-generation tasks with Llama and Mistral show that Grad-ELLM achieves strong comprehensiveness-oriented faithfulness under π-Soft-NC, while there is no dominant method under π-Soft-NS. Our evaluation metric serves as a rigorous framework to compare XAI methods for LLMs, which will support progress in the field.

Counting and tracking dense crowds in large-scale scenes is a highly practical yet challenging problem. Existing methods mostly rely on fixed-camera datasets with limited scene coverage, making them inadequate for crowd analysis in large-scale scenes. To bridge this gap, we introduce MovingDroneCrowd++, the largest video-level dataset dedicated to dense crowd counting and tracking with fast-moving drones, captured under diverse flight altitudes, camera angles, and illumination conditions. Existing methods, however, still fail to achieve satisfactory video individual counting or tracking performance under these challenging aerial conditions. To this end, we propose GD3A (Global Density map Decomposition via group-wise Descriptor Association), a video individual counting method that first establishes pixel-level correspondences between pedestrian descriptors across frames via optimal transport with an adaptive dustbin score. Then, group-wise association is adopted to guide the decomposition of the global density map into shared, inflow, and outflow density maps. We further introduce a pedestrian tracking method, DVTrack (Descriptor Voting Track), which converts descriptor-level matching into instance-level association through descriptor voting. Our methods rely on the association results of group-wise multiple descriptors for each pedestrian rather than a single vector. Since intra-group matching errors do not affect the final counting and tracking results, our methods are more robust in dense crowds and challenging aerial conditions. Experiments show that our methods achieve substantial gains in both crowd counting and tracking on moving-drone videos with dense crowds and complex motions, reducing counting error by 47.4

Employing Multimodal Large Language Models (MLLMs) for long video understanding remains a challenging problem due to the dilemma between the substantial number of video frames (i.e., visual tokens) versus the limited context length of language models. Traditional uniform sampling often leads to selection of irrelevant content, while post-training MLLMs on thousands of frames imposes a substantial computational burden. In this paper, we propose threading keyframes with narratives (Nar-KFC), a plug-and-play module to facilitate effective and efficient long video perception. Nar-KFC generally involves two collaborative steps. First, we formulate the keyframe selection process as an integer quadratic programming problem, jointly optimizing query-relevance and frame-diversity. To avoid its computational complexity, a customized greedy search strategy is designed as an efficient alternative. Second, to mitigate the temporal discontinuity caused by sparse keyframe sampling, we further introduce interleaved textual narratives generated from non-keyframes using off-the-shelf captioners. These narratives are inserted between keyframes based on their true temporal order, forming a coherent and compact representation. Nar-KFC thus serves as a temporal- and content-aware compression strategy that complements visual and textual modalities. Experimental results on multiple long-video benchmarks demonstrate that Nar-KFC significantly improves the performance of popular MLLMs. Code will be made publicly available.

Editing videos with textual guidance has garnered popularity due to its streamlined process which mandates users to solely edit the text prompt corresponding to the source video. Recent studies have explored and exploited large-scale text-to-image diffusion models for text-guided video editing, resulting in remarkable video editing capabilities. However, they may still suffer from some limitations such as mislocated objects, incorrect number of objects. Therefore, the controllability of video editing remains a formidable challenge. In this paper, we aim to challenge the above limitations by proposing a Re-Attentional Controllable Video Diffusion Editing (ReAtCo) method. Specially, to align the spatial placement of the target objects with the edited text prompt in a training-free manner, we propose a Re-Attentional Diffusion (RAD) to refocus the cross-attention activation responses between the edited text prompt and the target video during the denoising stage, resulting in a spatially location-aligned and semantically high-fidelity manipulated video. In particular, to faithfully preserve the invariant region content with less border artifacts, we propose an Invariant Region-guided Joint Sampling (IRJS) strategy to mitigate the intrinsic sampling errors w.r.t the invariant regions at each denoising timestep and constrain the generated content to be harmonized with the invariant region content. Experimental results verify that ReAtCo consistently improves the controllability of video diffusion editing and achieves superior video editing performance.

Multi-view crowd counting and localization fuse the input multi-views for estimating the crowd number or locations on the ground. Existing methods mainly focus on accurately predicting on the crowd shown in the input views, which neglects the problem of choosing the `best' camera views to perceive all crowds well in the scene. Besides, existing view selection methods require massive labeled views and images, and lack the ability for cross-scene settings, reducing their application scenarios. Thus, in this paper, we study the view selection issue for better scene-level multi-view crowd counting and localization results with cross-scene ability and limited label demand, instead of input-view-level results. We first propose an independent view selection method (IVS) that considers view and scene geometries in the view selection strategy and conducts the view selection, labeling, and downstream tasks independently. Based on IVS, we also put forward an active view selection method (AVS) that jointly conducts the view selection, labeling, and downstream tasks. In AVS, we actively select the labeled views and consider both the view/scene geometries and the predictions of the downstream task models in the view selection process. Experiments on multi-view counting and localization tasks demonstrate the cross-scene and the limited label demand advantages of the proposed active view selection method (AVS), outperforming existing methods and with wider application scenarios.

Audio Descriptions (ADs) aim to provide a narration of a movie in text form, describing non-dialogue-related narratives, such as characters, actions, or scene establishment. Automatic generation of ADs remains challenging due to: i) the domain gap between movie-AD data and existing data used to train vision-language models, and ii) the issue of contextual redundancy arising from highly similar neighboring visual clips in a long movie. In this work, we propose DistinctAD, a novel two-stage framework for generating ADs that emphasize distinctiveness to produce better narratives. To address the domain gap, we introduce a CLIP-AD adaptation strategy that does not require additional AD corpora, enabling more effective alignment between movie and AD modalities at both global and fine-grained levels. In Stage-II, DistinctAD incorporates two key innovations: (i) a Contextual Expectation-Maximization Attention (EMA) module that reduces redundancy by extracting common bases from consecutive video clips, and (ii) an explicit distinctive word prediction loss that filters out repeated words in the context, ensuring the prediction of unique terms specific to the current AD. Comprehensive evaluations on MAD-Eval, CMD-AD, and TV-AD benchmarks demonstrate the superiority of DistinctAD, with the model consistently outperforming baselines, particularly in Recall@k/N, highlighting its effectiveness in producing high-quality, distinctive ADs.

Occlusion is one of the fundamental challenges in crowd counting. In the community, various data-driven approaches have been developed to address this issue, yet their effectiveness is limited. This is mainly because most existing crowd counting datasets on which the methods are trained are based on passive cameras, restricting their ability to fully sense the environment. Recently, embodied navigation methods have shown significant potential in precise object detection in interactive scenes. These methods incorporate active camera settings, holding promise in addressing the fundamental issues in crowd counting. However, most existing methods are designed for indoor navigation, showing unknown performance in analyzing complex object distribution in large scale scenes, such as crowds. Besides, most existing embodied navigation datasets are indoor scenes with limited scale and object quantity, preventing them from being introduced into dense crowd analysis. Based on this, a novel task, Embodied Crowd Counting (ECC), is proposed. We first build up an interactive simulator, Embodied Crowd Counting Dataset (ECCD), which enables large scale scenes and large object quantity. A prior probability distribution that approximates realistic crowd distribution is introduced to generate crowds. Then, a zero-shot navigation method (ZECC) is proposed. This method contains a MLLM driven coarse-to-fine navigation mechanism, enabling active Z-axis exploration, and a normal-line-based crowd distribution analysis method for fine counting. Experimental results against baselines show that the proposed method achieves the best trade-off between counting accuracy and navigation cost.

Complex video reasoning remains a significant challenge for Multimodal Large Language Models (MLLMs), as current R1-based methodologies often prioritize text-centric reasoning derived from text-based and image-based developments. In video tasks, such strategies frequently underutilize rich visual information, leading to potential shortcut learning and increased susceptibility to hallucination. To foster a more robust, visual-centric video understanding, we start by introducing a novel self-supervised reinforcement learning GRPO algorithm (Pretext-GRPO) within the standard R1 pipeline, in which positive rewards are assigned for correctly solving pretext tasks on transformed visual inputs, which makes the model to non-trivially process the visual information. Building on the effectiveness of Pretext-GRPO, we further propose the ViSS-R1 framework, which streamlines and integrates pretext-task-based self-supervised learning directly into the MLLM's R1 post-training paradigm. Instead of relying solely on sparse visual cues, our framework compels models to reason about transformed visual input by simultaneously processing both pretext questions (concerning transformations) and true user queries. This necessitates identifying the applied transformation and reconstructing the original video to formulate accurate final answers. Comprehensive evaluations on six widely-used video reasoning and understanding benchmarks demonstrate the effectiveness and superiority of our Pretext-GRPO and ViSS-R1 for complex video reasoning. Our codes and models will be publicly available.

Visual explanation methods have been effective in interpreting the outputs of object detectors by highlighting important regions corresponding to each model prediction. However, existing approaches have largely overlooked inter-object relationships-particularly the relative importance of each pixel across different objects, a concept we refer to as Object Discrimination (OD). In this paper, we propose difference maps, a novel visual explanation technique designed to enhance the interpretability of object detectors with respect to OD. Serving as a complementary tool to existing instance-specific heat maps, difference maps improve their ability to isolate the impact of key features of individual objects on model outputs. Our qualitative and quantitative evaluation results show that the proposed difference maps can effectively distinguish key features specific to the target object, capturing the relative importance of each pixel across different predictions within the same scene. Our method is applicable to a wide range of object detectors, including one-stage, two-stage, and transformer-based architectures. Furthermore, it enhances existing heatmap-based visual explanation methods by improving focus on the detected object. These results demonstrate the utility of our approach in improving model transparency and inter-pretability across different detection architectures and explanation techniques.

The Visual Object Tracking Segmentation VOTS2024 challenge is the twelfth annual tracker benchmarking activity of the VOT initiative. This challenge consolidates the new tracking setup proposed in VOTS2023, which merges short-term and long-term as well as single-target and multiple-target tracking with segmentation masks as the only target location specification. Two sub-challenges are considered. The VOTS2024 standard challenge, focusing on classical objects and the VOTSt2024, which considers objects undergoing a topological transformation. Both challenges use the same performance evaluation methodology. Results of 28 submissions are presented and analyzed. A leaderboard, with participating trackers details, the source code, the datasets, and the evaluation kit are publicly available on the website (https://www.votchallenge.net/vots2024/).

Gaze estimation methods commonly rely on single-camera facial appearance analysis to estimate the direction of a person’s gaze. Recently, there has been significant interest in exploring gaze estimation techniques across different domains. Despite the advances, distinguishing authentic gaze-relevant features primarily relies on detecting subtle changes in the eye region. Moreover, non-gaze-related features are intricately entangled with the gaze-relevant components in a nonlinear manner. In response to these challenges, our work addresses the cross-domain gaze estimation problem through a feature decontaminating approach. Specifically, we propose a Cross Gaze Generalization (CGaG) method that explicitly encodes gaze- and domain-dedicated feature and leverages cross-identity features swapping to generate novel images where changes are exclusively confined to either the gaze or domain attributes. To consolidate feature purification and domain generalization, we utilize the equivariance between images and gaze labels to facilitate collaborative contrastive learning (CCL), which faithfully ensures that the generated novel images align with the expected outputs. Extensive experiments are conducted on various cross-domain tasks, demonstrating the effectiveness of CGaG. Meanwhile, CGaG achieves superior or comparable gaze estimation accuracy on both domain generalization and domain adaptation experiments. CGaG also shows promising cross-identity gaze or domain transfer visualizations.

Video Individual Counting (VIC) has received increasing attention for its importance in intelligent video surveillance. Existing works are limited in two aspects, i.e., dataset and method. Previous datasets are captured with fixed or rarely moving cameras with relatively sparse individuals, restricting evaluation for a highly varying view and time in crowded scenes. Existing methods rely on localization followed by association or classification, which struggle under dense and dynamic conditions due to inaccurate localization of small targets. To address these issues, we introduce the MovingDroneCrowd Dataset, featuring videos captured by fast-moving drones in crowded scenes under diverse illuminations, shooting heights and angles. We further propose a Shared Density map-guided Network (SDNet) using a Depth-wise Cross-Frame Attention (DCFA) module to directly estimate shared density maps between consecutive frames, from which the inflow and outflow density maps are derived by subtracting the shared density maps from the global density maps. The inflow density maps across frames are summed up to obtain the number of unique pedestrians in a video. Experiments on our datasets and publicly available ones show the superiority of our method over the state of the arts in highly dynamic and complex crowded scenes. Our dataset and codes have been released publicly.

Multi-view crowd counting has been proposed to deal with the severe occlusion issue of crowd counting in large and wide scenes. However, due to the difficulty of collecting and annotating multi-view images, the datasets for multi-view counting have a limited number of multi-view frames and scenes. To solve the problem of limited data, one approach is to collect synthetic data to bypass the annotating step, while another is to propose semi- or weakly-supervised or unsupervised methods that demand less multi-view data. In this paper, we propose two semi-supervised multi-view crowd counting frameworks by ranking the multi-view fusion models of different numbers of input views, in terms of the model predictions or the model uncertainties. Specifically, for the first method (vanilla model), we rank the multi-view fusion models' prediction results of different numbers of camera-view inputs, namely, the model's predictions with fewer camera views shall not be larger than the predictions with more camera views. For the second method, we rank the estimated model uncertainties of the multi-view fusion models with a variable number of view inputs, guided by the multi-view fusion models' prediction errors, namely, the model uncertainties with more camera views shall not be larger than those with fewer camera views. These constraints are introduced into the model training in a semi-supervised fashion for multi-view counting with limited labeled data. The experiments demonstrate the advantages of the proposed multi-view model ranking methods compared with other semi-supervised counting methods.

With the rise of social media, vast amounts of user-uploaded videos (e.g., YouTube) are utilized as training data for Visual Object Tracking (VOT). However, the VOT community has largely overlooked video data-privacy issues, as many private videos have been collected and used for training commercial models without authorization. To alleviate these issues, this paper presents the first investigation on preventing personal video data from unauthorized exploitation by deep trackers. Existing methods for preventing unauthorized data use primarily focus on image-based tasks (e.g., image classification), directly applying them to videos reveals several limitations, including inefficiency, limited effectiveness, and poor generalizability. To address these issues, we propose a novel generative framework for generating Temporal Unlearnable Examples (TUEs), and whose efficient computation makes it scalable for usage on large-scale video datasets. The trackers trained w/ TUEs heavily rely on unlearnable noises for temporal matching, ignoring the original data structure and thus ensuring training video data-privacy. To enhance the effectiveness of TUEs, we introduce a temporal contrastive loss, which further corrupts the learning of existing trackers when using our TUEs for training. Extensive experiments demonstrate that our approach achieves state-of-the-art performance in video data-privacy protection, with strong transferability across VOT models, datasets, and temporal matching tasks.

Crowd counting and localization involve extracting the number and distribution of crowds from images or videos using computer vision techniques. Most counting methods are based on density regression and are based on an ``intersection'' hypothesis, *i.e.*, one pixel is influenced by multiple points in the ground truth, which is inconsistent with reality since one pixel would not contain two objects. This paper proposes Proximal Mapping Loss (PML), a density regression method that eliminates this hypothesis. {PML} divides the predicted density map into multiple point-neighbor cases through the nearest neighbor, and then dynamically constructs a learning target for each sub-case via proximal mapping, leading to more robust and accurate training. {Furthermore}, PML is theoretically linked to various existing loss functions, such as Gaussian-blurred L2 loss, Bayesian loss, and the training schemes in P2PNet and DMC, demonstrating its versatility and adaptability. Experimentally, PML significantly improves the performance of crowd counting and localization, and illustrates the robustness against annotation noise. The code is available at [https://github.com/Elin24/pml](https://github.com/Elin24/pml).