相关论文: Benchmarking Data Efficiency and Computational Eff…

Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled…

Recently, Weakly-supervised Temporal Action Localization (WTAL) has been densely studied but there is still a large gap between weakly-supervised models and fully-supervised models. It is practical and intuitive to annotate temporal…

Understanding human activity is very challenging even with the recently developed 3D/depth sensors. To solve this problem, this work investigates a novel deep structured model, which adaptively decomposes an activity instance into temporal…

Video foundation models achieve strong performance across many video understanding tasks, but typically require large-scale pre-training on massive video datasets, resulting in substantial data and compute costs. In contrast, modern image…

This work tackles Weakly Supervised Anomaly detection, in which a predictor is allowed to learn not only from normal examples but also from a few labeled anomalies made available during training. In particular, we deal with the localization…

Detecting actions in videos have been widely applied in on-device applications. Practical on-device videos are always untrimmed with both action and background. It is desirable for a model to both recognize the class of action and localize…

Recently, temporal action localization (TAL) has garnered significant interest in information retrieval community. However, existing supervised/weakly supervised methods are heavily dependent on extensive labeled temporal boundaries and…

Deep learning models trained on large data sets have been widely successful in both vision and language domains. As state-of-the-art deep learning architectures have continued to grow in parameter count so have the compute budgets and times…

Temporal action localization (TAL) is a fundamental yet challenging task in video understanding. Existing TAL methods rely on pre-training a video encoder through action classification supervision. This results in a task discrepancy problem…

Deep-Learning-based video recognition has shown promising improvements along with the development of large-scale datasets and spatiotemporal network architectures. In image recognition, learning spatially invariant features is a key factor…

This paper describes a memory-efficient transformer model designed to drive a reduction in memory usage and execution time by substantial orders of magnitude without impairing the model's performance near that of the original model.…

Current fully-supervised video datasets consist of only a few hundred thousand videos and fewer than a thousand domain-specific labels. This hinders the progress towards advanced video architectures. This paper presents an in-depth study of…

In this work, we propose an approach to the spatiotemporal localisation (detection) and classification of multiple concurrent actions within temporally untrimmed videos. Our framework is composed of three stages. In stage 1, appearance and…

In most practical settings and theoretical analyses, one assumes that a model can be trained until convergence. However, the growing complexity of machine learning datasets and models may violate such assumptions. Indeed, current approaches…

Recently, multimodal tasks have strongly advanced the field of action recognition with their rich multimodal information. However, due to the scarcity of tri-modal data, research on tri-modal action recognition tasks faces many challenges.…

Video action detectors are usually trained using datasets with fully-supervised temporal annotations. Building such datasets is an expensive task. To alleviate this problem, recent methods have tried to leverage weak labeling, where videos…

Efficiency is an important issue in designing video architectures for action recognition. 3D CNNs have witnessed remarkable progress in action recognition from videos. However, compared with their 2D counterparts, 3D convolutions often…

Long-form video understanding requires designing approaches that are able to temporally localize activities or language. End-to-end training for such tasks is limited by the compute device memory constraints and lack of temporal annotations…

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…

Neural activity forecasting is central to understanding neural systems and enabling closed-loop control. While deep learning has recently advanced the state-of-the-art in the time series forecasting literature, its application to neural…