Related papers: Extending Temporal Data Augmentation for Video Act…
There has been huge progress on video action recognition in recent years. However, many works focus on tweaking existing 2D backbones due to the reliance of ImageNet pretraining, which restrains the models from achieving higher efficiency…
Performing data augmentation for learning deep neural networks is well known to be important for training visual recognition systems. By artificially increasing the number of training examples, it helps reducing overfitting and improves…
Recognizing human actions in videos requires spatial and temporal understanding. Most existing action recognition models lack a balanced spatio-temporal understanding of videos. In this work, we propose a novel two-stream architecture,…
Video large language models have achieved remarkable performance in tasks such as video question answering, however, their temporal understanding remains suboptimal. To address this limitation, we curate a dedicated instruction fine-tuning…
We propose a method for human action recognition, one that can localize the spatiotemporal regions that `define' the actions. This is a challenging task due to the subtlety of human actions in video and the co-occurrence of contextual…
Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often suffers from a substantial visual domain gap and limited…
In this paper, we introduce the latest solution developed by our team, HFUT-VUT, for the Micro-gesture Online Recognition track of the IJCAI 2025 MiGA Challenge. The Micro-gesture Online Recognition task is a highly challenging problem that…
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention. In this work, we propose a novel method that can effectively incorporate…
Contemporary Video Instance Segmentation (VIS) methods typically adhere to a pre-train then fine-tune regime, where a segmentation model trained on images is fine-tuned on videos. However, the lack of temporal knowledge in the pre-trained…
Deep learning models, in particular \textit{image} models, have recently gained generalisability and robustness. %are becoming more general and robust by the day. In this work, we propose to exploit such advances in the realm of…
Action recognition, an essential component of computer vision, plays a pivotal role in multiple applications. Despite significant improvements brought by Convolutional Neural Networks (CNNs), these models suffer performance declines when…
Transformers have recently been popular for learning and inference in the spatial-temporal domain. However, their performance relies on storing and applying attention to the feature tensor of each frame in video. Hence, their space and time…
Optimization of image transformation functions for the purpose of data augmentation has been intensively studied. In particular, adversarial data augmentation strategies, which search augmentation maximizing task loss, show significant…
Videos are more well-organized curated data sources for visual concept learning than images. Unlike the 2-dimensional images which only involve the spatial information, the additional temporal dimension bridges and synchronizes multiple…
In this paper, we explore and compare multiple solutions to the problem of data augmentation in image classification. Previous work has demonstrated the effectiveness of data augmentation through simple techniques, such as cropping,…
Temporal cues in videos provide important information for recognizing actions accurately. However, temporal-discriminative features can hardly be extracted without using an annotated large-scale video action dataset for training. This paper…
Data augmentation methods in combination with deep neural networks have been used extensively in computer vision on classification tasks, achieving great success; however, their use in time series classification is still at an early stage.…
The goal of human action recognition is to temporally or spatially localize the human action of interest in video sequences. Temporal localization (i.e. indicating the start and end frames of the action in a video) is referred to as…
We propose TubeR: a simple solution for spatio-temporal video action detection. Different from existing methods that depend on either an off-line actor detector or hand-designed actor-positional hypotheses like proposals or anchors, we…
Spatio-temporal action detection is an important and challenging problem in video understanding. However, the application of the existing large-scale spatio-temporal action datasets in specific fields is limited, and there is currently no…