1. THUMOS’14

1.1. End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames

• 2023 인용 x
• https://arxiv.org/pdf/2311.17241v1.pdf

1.2. Internvideo: General video foundation models via generative and discriminative learning

• 2022, 118회 인용
• https://arxiv.org/pdf/2212.03191.pdf

1.3. Temporal Action Localization with Enhanced Instant Discriminability

• 2023, 1회 인용
• https://arxiv.org/pdf/2309.05590v1.pdf

1.4. VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking

• 2023, 95회 인용
• https://arxiv.org/pdf/2303.16727v2.pdf
• https://velog.io/@hsbc/VideoMAE-V2-Scaling-Video-Masked-Autoencoders-with-Dual-Masking

1.5. TriDet: Temporal Action Detection with Relative Boundary Modeling

• 2023, 33회 인용
• https://openaccess.thecvf.com/content/CVPR2023/papers/Shi_TriDet_Temporal_Action_Detection_With_Relative_Boundary_Modeling_CVPR_2023_paper.pdf
• https://velog.io/write?id=f2d39bd1-3657-4c95-8999-064491839ce8

1.6. Action Sensitivity Learning for Temporal Action Localization

• X

1.7. ActionFormer: Localizing Moments of Actions with Transformers

• 2022, 191회 인용
• https://arxiv.org/pdf/2202.07925.pdf
• https://velog.io/@hsbc/ActionFormer-Localizing-Moments-of-Actions-with-Transformers-0mgzur05

2. 최신 순

2.1. Revisiting Foreground and Background Separation in Weakly-supervised Temporal Action Localization: A Clustering-based Approach

• https://arxiv.org/pdf/2312.14138v1.pdf

2.2. Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection

• https://arxiv.org/pdf/2311.16464v1.pdf

2.3. End-to-End Temporal Action Detection with 1B Parameters Across 1000 Frames

• https://arxiv.org/pdf/2311.17241v1.pdf

2.4. HR-Pro: Point-supervised Temporal Action Localization via Hierarchical Reliability Propagation

• https://arxiv.org/pdf/2308.12608v3.pdf

2.5. UnLoc: A Unified Framework for Video Localization Tasks

• https://arxiv.org/pdf/2308.11062v1.pdf

2.6. Masked Motion Predictors are Strong 3D Action Representation Learners

• https://arxiv.org/pdf/2308.07092v1.pdf

3. 그외

Proposal Relation Network for Temporal Action Detection

• 2021, 21회 인용
• https://arxiv.org/pdf/2106.11812v1.pdf

VideoCLIP: Contrastive Pre-training for Zero-shot Video-Text Understanding

• 2021, 326회 인용
• https://arxiv.org/pdf/2109.14084v2.pdf

TemporalMaxer: Maximize Temporal Context with only Max Pooling for Temporal Action Localization

• 2023, 6회 인용
• https://arxiv.org/pdf/2303.09055v1.pdf