mlsanityData to 14 Oct 2026

Leveraging Vision-Language Pre-training for Human Activity Recognition in Still Images

arXiv 2506.13458 ↗First posted 16 Jun 2025cs.CV cs.CLcited by 0

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

Abstract (arXiv)

Recognising human activity in a single photo enables indexing, safety and assistive applications, yet lacks motion cues. Using 285 MSCOCO images labelled as walking, running, sitting, and standing, scratch CNNs scored 41% accuracy. Fine-tuning multimodal CLIP raised this to 76%, demonstrating that contrastive vision-language pre-training decisively improves still-image action recognition in real-world deployments.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Video understanding with MLLMs, one of 16 directions in Multimodal LLMs / vision-language models. Builds on 7 of its 9 references that are in the map. First posted on arXiv 16 Jun 2025.

Builds on

7 of 9 references.

References · 7

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  4. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  5. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  6. 2015An Introduction to Convolutional Neural Networkscited by 514
  7. 2024LeGrad: An Explainability Method for Vision Transformers via Feature Formation Sensitivitycited by 33

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025Few-shot Vision-based Human Activity Recognition with MLLM-based Visual Reinforcement Learning
  2. 2023ZEETAD: Adapting Pretrained Vision-Language Model for Zero-Shot End-to-End Temporal Action Detection
  3. 2025Advancing Vision-based Human Action Recognition: Exploring Vision-Language CLIP Model for Generalisation in Domain-Independent Tasks
  4. 2023Expanding Frozen Vision-Language Models without Retraining: Towards Improved Robot Perception
  5. 2023VicTR: Video-conditioned Text Representations for Activity Recognition
  6. 2025Vision Language Models for Dynamic Human Activity Recognition in Healthcare Settings
  7. 2022Vision-Language Pre-training: Basics, Recent Advances, and Future Trends
  8. 2024Are Visual-Language Models Effective in Action Recognition? A Comparative Study