Understanding human behavior and activity facilitates advancement of numerous real-world
applications, and is critical for video analysis. Despite the progress of action recognition …

摘要视觉理解, 如物体检测, 语义和实例分割以及动作识别等, 在人机交互和自动驾驶等领域中
有着广泛的应用并发挥着至关重要的作用. 近年来, 基于全监督学习的深度视觉理解网络取得了 …

We tackle the problem of localizing temporal intervals of actions with only a single frame
label for each action instance for training. Owing to label sparsity, existing work fails to learn …

Open-vocabulary semantic segmentation is a challenging task that requires segmenting
novel object categories at inference time. Recent works explore vision-language pre-training …

Weakly-supervised temporal action localization aims to detect action boundaries in
untrimmed videos with only video-level annotations. Most existing schemes detect temporal …

Weakly-supervised temporal action localization (WTAL) learns to detect and classify action
instances with only category labels. Most methods widely adopt the off-the-shelf …

Audio-visual segmentation (AVS) aims to segment the sounding objects in video frames.
Although great progress has been witnessed we experimentally reveal that current methods …

In this paper, we consider the problem of temporal action localization under low-shot (zero-
shot & few-shot) scenario, with the goal of detecting and classifying the action instances from …

Point-level weakly-supervised temporal action localization (P-WSTAL) aims to localize
temporal extents of action instances and identify the corresponding categories with only a …

Temporal sentence grounding aims to detect the event timestamps described by the natural
language query from given untrimmed videos. The existing fully-supervised setting achieves …