相关论文: LoSA: Long-Short-range Adapter for Scaling End-to-…
Most recent approaches for action recognition from video leverage deep architectures to encode the video clip into a fixed length representation vector that is then used for classification. For this to be successful, the network must be…
Existing Vision-Language-Action (VLA) models can be broadly categorized into diffusion-based and auto-regressive (AR) approaches: diffusion models capture continuous action distributions but rely on computationally heavy iterative…
Weakly supervised video object localization (WSVOL) allows locating object in videos using only global video tags such as object class. State-of-art methods rely on multiple independent stages, where initial spatio-temporal proposals are…
We present a semi-supervised learning approach to the temporal action segmentation task. The goal of the task is to temporally detect and segment actions in long, untrimmed procedural videos, where only a small set of videos are densely…
Temporal modeling is crucial for various video learning tasks. Most recent approaches employ either factorized (2D+1D) or joint (3D) spatial-temporal operations to extract temporal contexts from the input frames. While the former is more…
While most modern video understanding models operate on short-range clips, real-world videos are often several minutes long with semantically consistent segments of variable length. A common approach to process long videos is applying a…
Current state-of-the-art models for video action recognition are mostly based on expensive 3D ConvNets. This results in a need for large GPU clusters to train and evaluate such architectures. To address this problem, we present a…
The rising popularity of large foundation models has led to a heightened demand for parameter-efficient fine-tuning methods, such as Low-Rank Adaptation (LoRA), which offer performance comparable to full model fine-tuning while requiring…
The crux of semi-supervised temporal action localization (SS-TAL) lies in excavating valuable information from abundant unlabeled videos. However, current approaches predominantly focus on building models that are robust to the error-prone…
Weakly supervised temporal action localization aims to localize temporal boundaries of actions and simultaneously identify their categories with only video-level category labels. Many existing methods seek to generate pseudo labels for…
Face analysis has been studied from different angles to infer emotion, poses, shapes, and landmarks. Traditionally RGB cameras are used, yet for fine-grained tasks standard sensors might not be up to the task due to their latency, making it…
Recent advancements in image understanding have benefited from the extensive use of web image-text pairs. However, video understanding remains a challenge despite the availability of substantial web video-text data. This difficulty…
Fully fine-tuning pretrained large-scale transformer models has become a popular paradigm for video-language modeling tasks, such as temporal language grounding and video-language summarization. With a growing number of tasks and limited…
Low-Rank Adaptation (LoRA) is widely adopted for downstream fine-tuning of foundation models due to its efficiency and zero additional inference cost. Many real-world applications require foundation models to specialize in several specific…
Temporal action localization (TAL) in videos is a challenging task, especially due to the large variation in action temporal scales. Short actions usually occupy a major proportion in the datasets, but tend to have the lowest performance.…
Video action recognition, which is topical in computer vision and video analysis, aims to allocate a short video clip to a pre-defined category such as brushing hair or climbing stairs. Recent works focus on action recognition with deep…
This paper focuses on temporal localization of actions in untrimmed videos. Existing methods typically train classifiers for a pre-defined list of actions and apply them in a sliding window fashion. However, activities in the wild consist…
Self-attention learns pairwise interactions to model long-range dependencies, yielding great improvements for video action recognition. In this paper, we seek a deeper understanding of self-attention for temporal modeling in videos. We…
Recent advances in training-free video editing have enabled lightweight and precise cross-frame generation by leveraging pre-trained text-to-image diffusion models. However, existing methods often rely on heuristic frame selection to…
Training temporal action detection in videos requires large amounts of labeled data, yet such annotation is expensive to collect. Incorporating unlabeled or weakly-labeled data to train action detection model could help reduce annotation…