mlsanityData to 7 Oct 2026

Text-Enhanced Zero-Shot Action Recognition: A training-free approach

arXiv 2408.16412 ↗First posted 29 Aug 2024cs.CVcited by 6

On the map: Multimodal LLMs / vision-language models → Video understanding with MLLMs

Abstract (arXiv)

Vision-language models (VLMs) have demonstrated remarkable performance across various visual tasks, leveraging joint learning of visual and textual representations. While these models excel in zero-shot image tasks, their application to zero-shot video action recognition (ZSVAR) remains challenging due to the dynamic and temporal nature of actions. Existing methods for ZS-VAR typically require extensive training on specific datasets, which can be resource-intensive and may introduce domain biases. In this work, we propose Text-Enhanced Action Recognition (TEAR), a simple approach to ZS-VAR that is training-free and does not require the availability of training data or extensive computational resources. Drawing inspiration from recent findings in vision and language literature, we utilize action descriptors for decomposition and contextual information to enhance zero-shot action recognition. Through experiments on UCF101, HMDB51, and Kinetics-600 datasets, we showcase the effectiveness and applicability of our proposed approach in addressing the challenges of ZS-VAR.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 32 of its 48 references that are in the map. First posted on arXiv 29 Aug 2024.

Builds on

32 of 48 references.

References · 32

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  4. 2017The Kinetics Human Action Video Datasetcited by 1,894
  5. 2021Open-vocabulary Object Detection via Vision and Language Knowledge Distillationcited by 903
  6. 2021DenseCLIP: Language-Guided Dense Prediction with Context-Aware Promptingcited by 530
  7. 2021Tip-Adapter: Training-free CLIP-Adapter for Better Vision-Language Modelingcited by 429
  8. 2018A Short Note about Kinetics-600cited by 331
  9. 2022Expanding Language-Image Pretrained Models for General Video Recognitioncited by 320
  10. 2021ActionCLIP: A New Paradigm for Video Action Recognitioncited by 317
  11. 2021Prompting Visual-Language Models for Efficient Video Understandingcited by 309
  12. 2022What does a platypus look like? Generating customized prompts for zero-shot image classificationcited by 263
20 more
  1. 2022Fine-tuned CLIP Models are Efficient Video Learnerscited by 178
  2. 2022Bridging the Gap between Object and Image-level Representations for Open-Vocabulary Detectioncited by 145
  3. 2023Waffling around for Performance: Visual Classification with Random Words and Broad Conceptscited by 100
  4. 2021Elaborative Rehearsal for Zero-shot Action Recognitioncited by 76
  5. 2023Verbs in Action: Improving verb understanding in video-language modelscited by 76
  6. 2022Revisiting Classifier: Transferring Vision-Language Models for Video Recognitioncited by 70
  7. 2023UnLoc: A Unified Framework for Video Localization Taskscited by 66
  8. 2022Zero-Shot Temporal Action Detection via Vision-Language Promptingcited by 65
  9. 2019Out-of-Distribution Detection for Generalized Zero-Shot Action Recognitioncited by 54
  10. 2020Temporal Interlacing Networkcited by 45
  11. 2023MAtch, eXpand and Improve: Unsupervised Finetuning for Zero-Shot Action Recognition with Language Knowledgecited by 43
  12. 2023Paxion: Patching Action Knowledge in Video-Language Foundation Modelscited by 42
  13. 2024FROSTER: Frozen CLIP Is A Strong Teacher for Open-Vocabulary Action Recognitioncited by 35
  14. 2024Test-Time Zero-Shot Temporal Action Localizationcited by 19
  15. 2017Zero-Shot Activity Recognition with Verb Attribute Inductioncited by 15
  16. 2023A Large-scale Study of Spatiotemporal Representation Learning with a New Benchmark on Action Recognitioncited by 14
  17. 2023Language-based Action Concept Spaces Improve Video Self-Supervised Learningcited by 10
  18. 2021Tell me what you see: A zero-shot action recognition method based on natural language descriptionscited by 7
  19. 2023Orthogonal Temporal Interpolation for Zero-Shot Video Recognitioncited by 6
  20. 2022Universal Prototype Transport for Zero-Shot Action Recognition and Localizationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 2; 2026: 4.

6 papers.

  1. 2025ActAlign: Zero-Shot Fine-Grained Video Classification via Language-Guided Sequence Alignmentcited by 3
  2. 2025Language as a Label: Zero-Shot Multimodal Classification of Everyday Postures under Data Scarcitycited by 1
  3. 2026Decompose and Transfer: CoT-Prompting Enhanced Alignment for Open-Vocabulary Temporal Action Detectioncited by 0
  4. 2026Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviorscited by 0
  5. 2026High-Speed Vision Improves Zero-Shot Semantic Understanding of Human Actionscited by 0
  6. 2026ConTrans: Learning Text-enhanced Local-global Temporal Representations for Zero-shot Temporal Action Localizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Enhancing Spatio-Temporal Zero-shot Action Recognition with Language-driven Description Attributes
  2. 2025Training-Free Zero-Shot Temporal Action Detection with Vision-Language Models
  3. 2026Zero-Shot Temporal Action Localization Through Textual Guidance
  4. 2026Exploring Vision-Language Models for Open-Vocabulary Zero-Shot Action Segmentation
  5. 2023ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
  6. 2026Novel Semantic Prompting for Zero-Shot Action Recognition
  7. 2025Text-driven Online Action Detection
  8. 2022VL-Taboo: An Analysis of Attribute-based Zero-shot Capabilities of Vision-Language Models