Related papers: STAR: Semantic-Temporal Adaptive Representation Le…

Semi-supervised temporal action segmentation (SS-TA) aims to perform frame-wise classification in long untrimmed videos, where only a fraction of videos in the training set have labels. Recent studies have shown the potential of contrastive…

Understanding the internal representations of large language models is crucial for ensuring their reliability and safety, with sparse autoencoders (SAEs) emerging as a promising interpretability approach. However, current SAE training…

Segmenting images is critical for visual understanding but demands extensive pixel-level annotations. Foundational models have enabled new paradigms for predicting new classes guided by textual prompts, without annotations from the target…

Self-Taught Reasoners (STaR), synonymously known as Rejection sampling Fine-Tuning (RFT), is an integral part of the training pipeline of self-improving reasoning Language Models (LMs). The self-improving mechanism often employs random…

For more efficient generalization to unseen domains (classes), most Few-shot Segmentation (FSS) would directly exploit pre-trained encoders and only fine-tune the decoder, especially in the current era of large models. However, such fixed…

As the development of cities, traffic congestion becomes an increasingly pressing issue, and traffic prediction is a classic method to relieve that issue. Traffic prediction is one specific application of spatio-temporal prediction…

For deep learning-based speech enhancement (SE) systems, the training-test acoustic mismatch can cause notable performance degradation. To address the mismatch issue, numerous noise adaptation strategies have been derived. In this paper, we…

Traditional temporal action localization (TAL) methods rely on large amounts of detailed annotated data, whereas few-shot TAL reduces this dependence by using only a few training samples to identify unseen action categories. However,…

Vision-language models (VLMs), despite their extraordinary zero-shot capabilities, are vulnerable to distribution shifts. Test-time adaptation (TTA) emerges as a predominant strategy to adapt VLMs to unlabeled test data on the fly. However,…

Few-shot segmentation (FSS) aims to rapidly learn novel class concepts from limited examples to segment specific targets in unseen images, and has been widely applied in areas such as medical diagnosis and industrial inspection. However,…

Anticipating human activities and their durations is essential in applications such as smart-home automation, simulation-based architectural and urban design, activity-based transportation system simulation, and human-robot collaboration,…

Synthetic aperture radar automatic target recognition (SAR-ATR) systems have rapidly evolved to tackle incremental recognition challenges in operational settings. Data scarcity remains a major hurdle that conventional SAR-ATR techniques…

Recent advancements in deep learning-based wearable human action recognition (wHAR) have improved the capture and classification of complex motions, but adoption remains limited due to the lack of expert annotations and domain discrepancies…

Correctly perceiving micro-expression is difficult since micro-expression is an involuntary, repressed, and subtle facial expression, and efficiently revealing the subtle movement changes and capturing the significant segments in a…

Sign language recognition (SLR) has long been plagued by insufficient model representation capabilities. Although current pre-training approaches have alleviated this dilemma to some extent and yielded promising performance by employing…

Deep models trained on a single source domain often fail catastrophically under distribution shifts, a critical challenge in Single Domain Generalization (SDG). While existing methods focus on augmenting source data or learning invariant…

Few-shot learning (FSL) aims to recognize novel concepts from only a few labeled support samples. Recent studies enhance support features by incorporating additional semantic information or designing complex semantic fusion modules.…

Self-supervised methods have shown remarkable progress in learning high-level semantics and low-level temporal correspondence. Building on these results, we take one step further and explore the possibility of integrating these two features…

Temporal action detection (TAD) is an important yet challenging task in video analysis. Most existing works draw inspiration from image object detection and tend to reformulate it as a proposal generation - classification problem. However,…

The zero-shot capabilities of Vision-Language Models (VLMs) have been widely leveraged to improve predictive performance. However, previous works on transductive or test-time adaptation (TTA) often make strong assumptions about the data…