Related papers: SVFormer: Semi-supervised Video Transformer for Ac…
Action detection is an essential and challenging task, especially for densely labelled datasets of untrimmed videos. The temporal relation is complex in those datasets, including challenges like composite action, and co-occurring action.…
Weakly-supervised Temporal Action Localization (WTAL) has achieved notable success but still suffers from a lack of temporal annotations, leading to a performance and framework gap compared with fully-supervised methods. While recent…
We introduce Knowledge Fusion Transformers for video action classification. We present a self-attention based feature enhancer to fuse action knowledge in 3D inception based spatio-temporal context of the video clip intended to be…
Video super-resolution (VSR) aims to restore a sequence of high-resolution (HR) frames from their low-resolution (LR) counterparts. Although some progress has been made, there are grand challenges to effectively utilize temporal dependency…
Learning with large-scale unlabeled data has become a powerful tool for pre-training Visual Transformers (VTs). However, prior works tend to overlook that, in real-world scenarios, the input data may be corrupted and unreliable.…
Supervised learning in large discriminative models is a mainstay for modern computer vision. Such an approach necessitates investing in large-scale human-annotated datasets for achieving state-of-the-art results. In turn, the efficacy of…
Temporal action localization is an important step towards video understanding. Most current action localization methods depend on untrimmed videos with full temporal annotations of action instances. However, it is expensive and…
In this paper, we propose a novel semi-supervised learning (SSL) framework named BoostMIS that combines adaptive pseudo labeling and informative active annotation to unleash the potential of medical image SSL models: (1) BoostMIS can…
Supervised deep learning methods for segmentation require large amounts of labelled training data, without which they are prone to overfitting, not generalizing well to unseen images. In practice, obtaining a large number of annotations…
In this paper, we introduce an innovative vector quantization based action tokenizer built upon the largest-scale action trajectory dataset to date, leveraging over 100 times more data than previous approaches. This extensive dataset…
Learning visual knowledge from massive weakly-labeled web videos has attracted growing research interests thanks to the large corpus of easily accessible video data on the Internet. However, for video action recognition, the action of…
Multi-view action recognition aims to recognize human actions using multiple camera views and deals with occlusion caused by obstacles or crowds. In this task, cooperation among views, which generates a joint representation by combining…
We present a novel data-efficient semi-supervised framework to improve the generalization of image captioning models. Constructing a large-scale labeled image captioning dataset is an expensive task in terms of labor, time, and cost. In…
Recent years have witnessed a trend of applying context frames to boost the performance of object detection as video object detection. Existing methods usually aggregate features at one stroke to enhance the feature. These methods, however,…
An important challenge in emotion recognition is to develop methods that can leverage unlabeled training data. In this paper, we propose the VQ-MAE-AV model, a self-supervised multimodal model that leverages masked autoencoders to learn…
Most popular deep learning based models for action recognition are designed to generate separate predictions within their short temporal windows, which are often aggregated by heuristic means to assign an action label to the full video…
Video action segmentation under timestamp supervision has recently received much attention due to lower annotation costs. Most existing methods generate pseudo-labels for all frames in each video to train the segmentation model. However,…
This paper investigates the effectiveness of self-supervised pre-trained vision transformers (ViTs) compared to supervised pre-trained ViTs and conventional neural networks (ConvNets) for detecting facial deepfake images and videos. It…
How can unlabeled video augment visual learning? Existing methods perform "slow" feature analysis, encouraging the representations of temporally close frames to exhibit only small differences. While this standard approach captures the fact…
This paper considers semi-supervised learning for tabular data. It is widely known that Xgboost based on tree model works well on the heterogeneous features while transductive support vector machine can exploit the low density separation…