相关论文: Learning from Temporal Gradient for Semi-supervise…

Fine-grained action recognition (FGAR) aims to identify subtle and distinctive differences among fine-grained action categories. However, current recognition methods often capture coarse-grained motion patterns but struggle to identify…

This work presents a self-supervised learning framework named TeG to explore Temporal Granularity in learning video representations. In TeG, we sample a long clip from a video and a short clip that lies inside the long clip. We then extract…

We propose a self-supervised method for learning motion-focused video representations. Existing approaches minimize distances between temporally augmented videos, which maintain high spatial similarity. We instead propose to learn…

We target at the task of weakly-supervised action localization (WSAL), where only video-level action labels are available during model training. Despite the recent progress, existing methods mainly embrace a localization-by-classification…

We present a novel approach for unsupervised activity segmentation which uses video frame clustering as a pretext task and simultaneously performs representation learning and online clustering. This is in contrast with prior works where…

Temporal action localization (TAL) involves dual tasks to classify and localize actions within untrimmed videos. However, the two tasks often have conflicting requirements for features. Existing methods typically employ separate heads for…

We propose a novel approach to the action segmentation task for long, untrimmed videos, based on solving an optimal transport problem. By encoding a temporal consistency prior into a Gromov-Wasserstein problem, we are able to decode a…

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…

We propose a technique that tackles action detection in multimodal videos under a realistic and challenging condition in which only limited training data and partially observed modalities are available. Common methods in transfer learning…

Self-supervised learning has shown great potentials in improving the deep learning model in an unsupervised manner by constructing surrogate supervision signals directly from the unlabeled data. Different from existing works, we present a…

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…

Contrastive learning has nearly closed the gap between supervised and self-supervised learning of image representations, and has also been explored for videos. However, prior work on contrastive learning for video data has not explored the…

Unsupervised video segmentation plays an important role in a wide variety of applications from object identification to compression. However, to date, fast motion, motion blur and occlusions pose significant challenges. To address these…

We propose a weakly-supervised framework for action labeling in video, where only the order of occurring actions is required during training time. The key challenge is that the per-frame alignments between the input (video) and label…

Temporal action localization presents a trade-off between test performance and annotation-time cost. Fully supervised methods achieve good performance with time-consuming boundary annotations. Weakly supervised methods with cheaper…

Though action recognition in videos has achieved great success recently, it remains a challenging task due to the massive computational cost. Designing lightweight networks is a possible solution, but it may degrade the recognition…

Most existing action quality assessment methods rely on the deep features of an entire video to predict the score, which is less reliable due to the non-transparent inference process and poor interpretability. We argue that understanding…

While many action recognition datasets consist of collections of brief, trimmed videos each containing a relevant action, videos in the real-world (e.g., on YouTube) exhibit very different properties: they are often several minutes long,…

Temporal Action Detection (TAD), the task of localizing and classifying actions in untrimmed video, remains challenging due to action overlaps and variable action durations. Recent findings suggest that TAD performance is dependent on the…

Spatio-temporal feature learning is of central importance for action recognition in videos. Existing deep neural network models either learn spatial and temporal features independently (C2D) or jointly with unconstrained parameters (C3D).…