相关论文: Temporal-attentive Covariance Pooling Networks for…
For weakly supervised anomaly detection, most existing work is limited to the problem of inadequate video representation due to the inability of modeling long-term contextual information. To solve this, we propose a novel weakly supervised…
Temporal grounding, which localizes video moments related to a natural language query, is a core problem of vision-language learning and video understanding. To encode video moments of varying lengths, recent methods employ a multi-level…
A video can be represented as a sequence of tracklets, each spanning 10-20 frames, and associated with one entity (eg. a person). The task of \emph{Entity Discovery} in videos can be naturally posed as tracklet clustering. We approach this…
The attribution method provides a direction for interpreting opaque neural networks in a visual way by identifying and visualizing the input regions/pixels that dominate the output of a network. Regarding the attribution method for visually…
Deep networks have been successfully applied to visual tracking by learning a generic representation offline from numerous training images. However the offline training is time-consuming and the learned generic representation may be less…
To equip artificial intelligence with a comprehensive understanding towards a temporal world, video and 4D panoptic scene graph generation abstracts visual data into nodes to represent entities and edges to capture temporal relations.…
Tracking Any Point (TAP) in a video is a challenging computer vision problem with many demonstrated applications in robotics, video editing, and 3D reconstruction. Existing methods for TAP rely heavily on complex tracking-specific inductive…
Temporal action recognition always depends on temporal action proposal generation to hypothesize actions and algorithms usually need to process very long video sequences and output the starting and ending times of each potential action in…
Skeleton-based action recognition methods are limited by the semantic extraction of spatio-temporal skeletal maps. However, current methods have difficulty in effectively combining features from both temporal and spatial graph dimensions…
General-purpose foundation models for neural time series can help accelerate neuroscientific discoveries and enable applications such as brain computer interfaces (BCIs). A key component in scaling these models is population-level…
Video colorization is a challenging and highly ill-posed problem. Although recent years have witnessed remarkable progress in single image colorization, there is relatively less research effort on video colorization and existing methods…
Point-Level temporal action localization (PTAL) aims to localize actions in untrimmed videos with only one timestamp annotation for each action instance. Existing methods adopt the frame-level prediction paradigm to learn from the sparse…
Succinct representation of complex signals using coordinate-based neural representations (CNRs) has seen great progress, and several recent efforts focus on extending them for handling videos. Here, the main challenge is how to (a)…
Attention mechanism, especially channel attention, has gained great success in the computer vision field. Many works focus on how to design efficient channel attention mechanisms while ignoring a fundamental problem, i.e., channel attention…
Downsampling-based methods for time series forecasting have attracted increasing attention due to their superiority in capturing sequence trends. However, this approaches mainly capture dependencies within subsequences but neglect…
Recent multi-frame lifting methods have dominated the 3D human pose estimation. However, previous methods ignore the intricate dependence within the 2D pose sequence and learn single temporal correlation. To alleviate this limitation, we…
Generalist Vision-Language-Action models are currently hindered by the scarcity of robotic data compared to the abundance of human video demonstrations. Existing Latent Action Models attempt to leverage video data but often suffer from…
The dominant paradigm for video-based action segmentation is composed of two steps: first, for each frame, compute low-level features using Dense Trajectories or a Convolutional Neural Network that encode spatiotemporal information locally,…
The task of temporally grounding language queries in videos is to temporally localize the best matched video segment corresponding to a given language (sentence). It requires certain models to simultaneously perform visual and linguistic…
Recent video recognition models utilize Transformer models for long-range spatio-temporal context modeling. Video transformer designs are based on self-attention that can model global context at a high computational cost. In comparison,…