Related papers: Faster Learning of Temporal Action Proposal via Sp…
Semi-supervised video action recognition tends to enable deep neural networks to achieve remarkable performance even with very limited labeled data. However, existing methods are mainly transferred from current image-based methods (e.g.,…
Temporal Video Grounding (TVG) aims to localize the temporal boundary of a specific segment in an untrimmed video based on a given language query. Since datasets in this domain are often gathered from limited video scenes, models tend to…
Temporal action detection in long videos is an important problem. State-of-the-art methods address this problem by applying action classifiers on sliding windows. Although sliding windows may contain an identifiable portion of the actions,…
Self-supervised learning has drawn attention through its effectiveness in learning in-domain representations with no ground-truth annotations; in particular, it is shown that properly designed pretext tasks (e.g., contrastive prediction…
Weakly-supervised temporal action localization aims to localize and recognize actions in untrimmed videos with only video-level category labels during training. Without instance-level annotations, most existing methods follow the…
Real-time video segmentation is a crucial task for many real-world applications such as autonomous driving and robot control. Since state-of-the-art semantic segmentation models are often too heavy for real-time applications despite their…
Given some video-query pairs with untrimmed videos and sentence queries, temporal sentence grounding (TSG) aims to locate query-relevant segments in these videos. Although previous respectable TSG methods have achieved remarkable success,…
Video Paragraph Grounding (VPG) is an emerging task in video-language understanding, which aims at localizing multiple sentences with semantic relations and temporal order from an untrimmed video. However, existing VPG approaches are…
Temporal Action Localization (TAL) remains a fundamental challenge in video understanding, aiming to identify the start time, end time, and category of all action instances within untrimmed videos. While recent single-stage, anchor-free…
RGB-Thermal Video Object Detection (RGBT VOD) can address the limitation of traditional RGB-based VOD in challenging lighting conditions, making it more practical and effective in many applications. However, similar to most RGBT fusion…
Temporal action detection aims to locate the boundaries of action in the video. The current method based on boundary matching enumerates and calculates all possible boundary matchings to generate proposals. However, these methods neglect…
Video Temporal Grounding (VTG) aims to extract relevant video segments based on a given natural language query. Recently, zero-shot VTG methods have gained attention by leveraging pretrained vision-language models (VLMs) to localize target…
Temporal action proposal generation is an important and challenging task in video understanding, which aims at detecting all temporal segments containing action instances of interest. The existing proposal generation approaches are…
Supervised approaches for learning spatio-temporal scene graphs (STSG) from video are greatly hindered due to their reliance on STSG-annotated videos, which are labor-intensive to construct at scale. Is it feasible to instead use readily…
Visual-based perception is the key module for autonomous driving. Among those visual perception tasks, video object detection is a primary yet challenging one because of feature degradation caused by fast motion or multiple poses. Current…
In computer animation, game design, and human-computer interaction, synthesizing human motion that aligns with user intent remains a significant challenge. Existing methods have notable limitations: textual approaches offer high-level…
Diffusion models deliver high quality in image synthesis but remain expensive during training and inference. Recent works have leveraged the inherent redundancy in visual content to make training more affordable by training only on a subset…
Temporal action proposals are a common module in action detection pipelines today. Most current methods for training action proposal modules rely on fully supervised approaches that require large amounts of annotated temporal action…
We propose a unified approach for bottom-up hierarchical image segmentation and object proposal generation for recognition, called Multiscale Combinatorial Grouping (MCG). For this purpose, we first develop a fast normalized cuts algorithm.…
Temporal sentence grounding (TSG) is crucial and fundamental for video understanding. Although the existing methods train well-designed deep networks with a large amount of data, we find that they can easily forget the rarely appeared cases…