TF-CADE: Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection

• URL: http://arxiv.org/abs/2608.17422v1
• Date: Tue, 18 Aug 2026 06:43:45 GMT
• Title: TF-CADE: Foreground-Concentrated Text-Video Alignment for Zero-Shot Temporal Action Detection
• Abstract summary: We propose a Text-Foreground Concentrated Alignment for zero-shot temporal action DEtector (TF-CADE)<n>ACA extracts action concentrate scores to aggregate temporally informative video segments into a foreground- weighted video embedding.<n> CCR strategy refines per-snippet confidence scores by lever- aging foreground-aware similarity, effectively suppressing irrelevant action classes during inference.
• Score: 54.38725298163703
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Zero-Shot Temporal Action Detection (ZSTAD) aims to lo- calize and recognize action instances from unseen action categories in untrimmed videos. Although existing meth- ods have shown effectiveness by advancing architectural text-video alignment, they still struggle with capturing se- mantic distinctions between action classes, resulting in text- irrelevant predictions. To address this issue, we propose a Text-Foreground Concentrated Alignment for zero-shot temporal action DEtector (TF-CADE) that explicitly aligns textual information with action-relevant foreground regions. Specifically, we introduce Action Concentrate Aggregation (ACA), which extracts action concentrate scores to aggregate temporally informative video segments into a foreground- weighted video embedding. This foreground concentrated alignment enhances the semantic consistency between text and video features and improves inter-class discriminabil- ity. In addition, a Certainty-based Confidence Re-weighting (CCR) strategy refines per-snippet confidence scores by lever- aging foreground-aware similarity, effectively suppressing irrelevant action classes during inference. Extensive evalua- tions show that our TF-CADE not only achieves state-of-the- art performance under in-distribution settings but also excels in cross-dataset generalization to unseen action classes.

Related papers

• Motion-Guided Semantic Alignment with Negative Prompts for Zero-Shot Video Action Recognition [12.523217686212197]
  We present a novel framework that enhances CLIP with disentangled embeddings and semantic-guided interaction.<n>Experiments on standard benchmarks demonstrate that our method consistently outperforms prior CLIP-based approaches.
  arXiv  Detail & Related papers  (2026-04-18T16:34:29Z)
• Classification Matters: Improving Video Action Detection with Class-Specific Attention [61.14469113965433]
  Video action detection (VAD) aims to detect actors and classify their actions in a video. We analyze how prevailing methods form features for classification and find that they prioritize actor regions. We propose to reduce the bias toward actor and encourage paying attention to the context that is relevant to each action class.
  arXiv  Detail & Related papers  (2024-07-29T04:43:58Z)
• FineParser: A Fine-grained Spatio-temporal Action Parser for Human-centric Action Quality Assessment [30.601466217201253]
  Existing action quality assessment (AQA) methods mainly learn deep representations at the video level for scoring diverse actions. Due to the lack of a fine-grained understanding of actions in videos, they harshly suffer from low credibility and interpretability, thus insufficient for stringent applications, such as Olympic diving events. We argue that a fine-grained understanding of actions requires the model to perceive and parse actions in both time and space, which is also the key to the credibility and interpretability of the AQA technique.
  arXiv  Detail & Related papers  (2024-05-11T02:57:16Z)
• Boosting Weakly-Supervised Temporal Action Localization with Text Information [94.48602948837664]
  We propose a Text-Segment Mining (TSM) mechanism, which constructs a text description based on the action class label, and regards the text as the query to mine all class-related segments. We also introduce a generative objective named Video-text Language Completion (VLC), which focuses on all semantic-related segments from videos to complete the text sentence. Surprisingly, we also find our proposed method can be seamlessly applied to existing methods, and improve their performances with a clear margin.
  arXiv  Detail & Related papers  (2023-05-01T00:07:09Z)
• Weakly-Supervised Temporal Action Localization with Bidirectional Semantic Consistency Constraint [83.36913240873236]
  Weakly Supervised Temporal Action localization (WTAL) aims to classify and localize temporal boundaries of actions for the video. We propose a simple yet efficient method, named bidirectional semantic consistency constraint (Bi- SCC) to discriminate the positive actions from co-scene actions. Experimental results show that our approach outperforms the state-of-the-art methods on THUMOS14 and ActivityNet.
  arXiv  Detail & Related papers  (2023-04-25T07:20:33Z)
• Fine-grained Temporal Contrastive Learning for Weakly-supervised Temporal Action Localization [87.47977407022492]
  This paper argues that learning by contextually comparing sequence-to-sequence distinctions offers an essential inductive bias in weakly-supervised action localization. Under a differentiable dynamic programming formulation, two complementary contrastive objectives are designed, including Fine-grained Sequence Distance (FSD) contrasting and Longest Common Subsequence (LCS) contrasting. Our method achieves state-of-the-art performance on two popular benchmarks.
  arXiv  Detail & Related papers  (2022-03-31T05:13:50Z)
• End-to-End Semi-Supervised Learning for Video Action Detection [23.042410033982193]
  We propose a simple end-to-end based approach effectively which utilizes the unlabeled data. Video action detection requires both, action class prediction as well as a-temporal consistency. We demonstrate the effectiveness of the proposed approach on two different action detection benchmark datasets.
  arXiv  Detail & Related papers  (2022-03-08T18:11:25Z)
• Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context [151.23835595907596]
  Methods learn to localize temporal starts and ends of action instances in a video under only video-level supervision. We introduce a framework that learns two feature subspaces respectively for actions and their context. The proposed approach outperforms state-of-the-art WS-TAL methods on three benchmarks.
  arXiv  Detail & Related papers  (2021-03-30T08:26:53Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.