Related references
Note: Only part of the references are listed.
Proceedings Paper
Computer Science, Artificial Intelligence
Junyu Gao et al.
Summary: This paper introduces a new weakly-supervised action localization method that improves the accuracy of action localization by comparing the differences between sequences in context. Experimental results demonstrate that the method achieves state-of-the-art performance on two popular benchmarks.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Zhaohui Zheng et al.
Summary: This paper presents a novel localization distillation (LD) method that efficiently transfers localization knowledge from a teacher model to a student model in object detection. The research findings demonstrate that localization knowledge distillation is more important and efficient than feature imitation and semantic knowledge for distilling object detectors.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Bo He et al.
Summary: Weakly-supervised temporal action localization aims to recognize and locate action segments in untrimmed videos using only video-level action labels. Existing methods mostly rely on multiple-instance learning, but ignore the temporal structure between action segments. To address this, we propose a novel framework that models action segments through three components and introduces a refinement strategy for progressive improvement of action proposals.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Linjiang Huang et al.
Summary: Weakly supervised temporal action localization aims to localize the temporal boundaries of actions and identify their categories using only video-level labels. Existing methods often generate limited pseudo labels, but our proposed representative snippet summarization and propagation framework improves this by mining representation snippets and propagating information. Our method achieves superior performance on two benchmarks and outperforms existing methods, with gains as high as 1.2% in terms of average mAP on THUMOS14.
2022 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2022)
(2022)
Article
Computer Science, Artificial Intelligence
Runhao Zeng et al.
Summary: This paper proposes a general graph convolutional module (GCM) to enhance the performance of temporal action localization methods. The relationships between action units are found to be important in action localization, and GCM is able to capture both the local content and the context of action units effectively.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2022)
Proceedings Paper
Computer Science, Artificial Intelligence
Linjiang Huang et al.
Summary: This paper introduces a framework called FAC-Net, which achieves efficient weakly supervised temporal action localization by maximizing foreground-background separation and regularizing foreground-action consistency. The method employs multiple branches and a hybrid attention mechanism, leading to state-of-the-art performance in the field.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Sanath Narayan et al.
Summary: The study introduces a weakly-supervised temporal action localization framework, D2-Net, with a novel loss formulation that enhances discriminability and robustness. By incorporating discriminative and denoising loss terms, the model achieves more accurate temporal action localization. Comprehensive experiments show that D2-Net outperforms existing methods on multiple benchmarks.
2021 IEEE/CVF INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV 2021)
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Junwei Ma et al.
Summary: The paper introduces the Action Selection Learning (ASL) approach to address the action localization problem in videos. By training the model to predict which frames will be selected by the classifier, it effectively captures the concept of actions. Empirically, ASL outperforms leading baselines on two popular benchmarks.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Wenfei Yang et al.
Summary: The proposed Uncertainty Guided Collaborative Training (UGCT) strategy effectively improves the performance of attention based methods for weakly supervised temporal action detection by generating pseudo labels online and mitigating noise in the generated labels. Experimental results show a significant performance improvement of more than 4% for all three methods on the THUMOS14 dataset.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Jinguo Zhu et al.
Summary: This paper introduces a novel knowledge distillation method, Complementary Relation Contrastive Distillation (CRCD), which transfers structural knowledge from teacher to student using anchor points. By maximizing mutual information between anchor-teacher and anchor-student relations, it effectively distills sample representations and inter-sample relations. Experimental results on various benchmarks demonstrate the effectiveness of the proposed CRCD.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Hanzhe Hu et al.
Summary: In this work, a Dense Relation Distillation with Context-aware Aggregation (DCNet) is proposed to address the few-shot object detection problem by fully exploiting support features and capturing fine-grained features. The model achieves state-of-the-art results on PASCAL VOC and MS COCO datasets, demonstrating the effectiveness of the proposed approach.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Wang Luo et al.
Summary: This paper introduces an Action Unit Memory Network (AUMN) for weakly supervised temporal action localization, which mitigates challenges by learning action unit memory bank and utilizes diverse mechanisms. It is the first to explicitly model action units with a memory network, showing superior performance compared to state-of-the-art methods on standard benchmarks.
2021 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION, CVPR 2021
(2021)
Proceedings Paper
Computer Science, Artificial Intelligence
Baifeng Shi et al.
2020 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2020)
Proceedings Paper
Computer Science, Artificial Intelligence
Daochang Liu et al.
2019 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2019)
(2019)
Proceedings Paper
Computer Science, Artificial Intelligence
Phuc Nguyen et al.
2018 IEEE/CVF CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR)
(2018)
Proceedings Paper
Computer Science, Artificial Intelligence
Krishna Kumar Singh et al.
2017 IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION (ICCV)
(2017)
Article
Computer Science, Artificial Intelligence
Haroon Idrees et al.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2017)
Proceedings Paper
Computer Science, Artificial Intelligence
Joao Carreira et al.
30TH IEEE CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION (CVPR 2017)
(2017)
Article
Computer Science, Artificial Intelligence
Adrien Gaidon et al.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2013)