Related papers: TALLFormer: Temporal Action Localization with a Lo…

We address the problem of temporal localization of repetitive activities in a video, i.e., the problem of identifying all segments of a video that contain some sort of repetitive or periodic motion. To do so, the proposed method represents…

Temporal action localization is a recently-emerging task, aiming to localize video segments from untrimmed videos that contain specific actions. Despite the remarkable recent progress, most two-stage action localization methods still suffer…

The Transformer architecture has revolutionized deep learning on sequential data, becoming ubiquitous in state-of-the-art solutions for a wide variety of applications. Yet vanilla Transformers are notoriously resource-expensive, requiring…

The role of long- and short-term dynamics towards salient object detection in videos is under-researched. We present a Transformer-based approach to learn a joint representation of video frames and past saliency information. Our model…

Temporal action localization is an important and challenging task that aims to locate temporal regions in real-world untrimmed videos where actions occur and recognize their classes. It is widely acknowledged that video context is a…

Summarizing video content is an important task in many applications. This task can be defined as the computation of the ordered list of actions present in a video. Such a list could be extracted using action detection algorithms. However,…

Weakly supervised temporal action localization aims at learning the instance-level action pattern from the video-level labels, where a significant challenge is action-context confusion. To overcome this challenge, one recent work builds an…

Temporal modelling is the key for efficient video action recognition. While understanding temporal information can improve recognition accuracy for dynamic actions, removing temporal redundancy and reusing past features can significantly…

Transformer-based models have achieved state-of-the-art results in a wide range of natural language processing (NLP) tasks including document summarization. Typically these systems are trained by fine-tuning a large pre-trained model to the…

Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel…

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…

Temporal forgery localization aims to temporally identify manipulated segments in videos. Most existing benchmarks focus on appearance-level forgeries, such as face swapping and object removal. However, recent advances in video generation…

This paper is a brief report to our submission to the VIPriors Action Recognition Challenge. Action recognition has attracted many researchers attention for its full application, but it is still challenging. In this paper, we study previous…

The widespread 'deeper is better' philosophy has driven the creation of architectures like ResNet and Transformer, which achieve high performance by stacking numerous layers. However, increasing model depth comes with challenges such as…

Due to the high price and heavy energy consumption of GPUs, deploying deep models on IoT devices such as microcontrollers makes significant contributions for ecological AI. Conventional methods successfully enable convolutional neural…

Extracting robust feature representation is critical for object re-identification to accurately identify objects across non-overlapping cameras. Although having a strong representation ability, the Vision Transformer (ViT) tends to overfit…

Pretrained Vision-Language-Action (VLA) policies have achieved strong single-step manipulation, but their inference remains largely memoryless, which is brittle in non-Markovian long-horizon settings with occlusion, state aliasing, and…

Many tasks in video analysis and understanding boil down to the need for frame-based feature learning, aiming to encapsulate the relevant visual content so as to enable simpler and easier subsequent processing. While supervised strategies…

While transformers demonstrate outstanding performance across various audio tasks, their application to neural vocoders remains challenging. Neural vocoders require the generation of long audio signals at the sample level, which demands…

Long-term time-series forecasting (LTSF) is fundamental to various real-world applications, where Transformer-based models have become the dominant framework due to their ability to capture long-range dependencies. However, these models…