相关论文: Towards Train-Test Consistency for Semi-supervised…

Training automatic speech recognition (ASR) systems requires large amounts of well-curated paired data. However, human annotators usually perform "non-verbatim" transcription, which can result in poorly trained models. In this paper, we…

Temporal action localization is an important yet challenging task in video understanding. Typically, such a task aims at inferring both the action category and localization of the start and end frame for each action instance in a long,…

Test-time Reinforcement Learning (TTRL) has shown promise in adapting foundation models for complex tasks at test-time, resulting in large performance improvements. TTRL leverages an elegant two-phase sampling strategy: first,…

Action recognition in videos has attracted a lot of attention in the past decade. In order to learn robust models, previous methods usually assume videos are trimmed as short sequences and require ground-truth annotations of each video…

Recent advances of deep learning have achieved remarkable performances in various challenging computer vision tasks. Especially in object localization, deep convolutional neural networks outperform traditional approaches based on extraction…

Convolutional neural networks can achieve remarkable performance in semantic segmentation tasks. However, such neural network approaches heavily rely on costly pixel-level annotation. Semi-supervised learning is a promising resolution to…

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 arbitrary categories within some untrimmed videos,…

Localizing actions in video is a core task in computer vision. The weakly supervised temporal localization problem investigates whether this task can be adequately solved with only video-level labels, significantly reducing the amount of…

The increasingly wide usage of location aware sensors has made it possible to collect large volume of trajectory data in diverse application domains. Machine learning allows to study the activities or behaviours of moving objects (e.g.,…

Despite the recent advances in video classification, progress in spatio-temporal action recognition has lagged behind. A major contributing factor has been the prohibitive cost of annotating videos frame-by-frame. In this paper, we present…

Nowadays, the interaction between humans and robots is constantly expanding, requiring more and more human motion recognition applications to operate in real time. However, most works on temporal action detection and recognition perform…

Temporal language grounding (TLG) is a fundamental and challenging problem for vision and language understanding. Existing methods mainly focus on fully supervised setting with temporal boundary labels for training, which, however, suffers…

Large Language Models (LLMs) deployed in agentic environments must exercise multiple capabilities across different task instances, where a capability is performing one or more actions in a trajectory that are necessary for successfully…

Tactile signals collected by wearable electronics are essential in modeling and understanding human behavior. One of the main applications of tactile signals is action classification, especially in healthcare and robotics. However, existing…

In this paper, we present a novel cross-consistency based semi-supervised approach for semantic segmentation. Consistency training has proven to be a powerful semi-supervised learning framework for leveraging unlabeled data under the…

As a challenging task of high-level video understanding, weakly supervised temporal action localization has been attracting increasing attention. With only video annotations, most existing methods seek to handle this task with a…

Due to the limited and even imbalanced data, semi-supervised semantic segmentation tends to have poor performance on some certain categories, e.g., tailed categories in Cityscapes dataset which exhibits a long-tailed label distribution.…

Most work on temporal action detection is formulated as an offline problem, in which the start and end times of actions are determined after the entire video is fully observed. However, important real-time applications including…

We propose a semi-supervised approach for contemporary object detectors following the teacher-student dual model framework. Our method is featured with 1) the exponential moving averaging strategy to update the teacher from the student…

This paper proposes a novel multi-modal transformer network for detecting actions in untrimmed videos. To enrich the action features, our transformer network utilizes a new multi-modal attention mechanism that computes the correlations…