Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

EgoNCE++: Do Egocentric Video-Language Models Really Understand Hand-Object Interactions? (2405.17719v2)

Published 28 May 2024 in cs.CV

Abstract: Egocentric video-language pretraining is a crucial paradigm to advance the learning of egocentric hand-object interactions (EgoHOI). Despite the great success on existing testbeds, these benchmarks focus more on closed-set visual concepts or limited scenarios. Due to the occurrence of diverse EgoHOIs in the real world, we propose an open-vocabulary benchmark named EgoHOIBench to reveal the diminished performance of current egocentric video-LLMs (EgoVLM) on fined-grained concepts, indicating that these models still lack a full spectrum of egocentric understanding. We attribute this performance gap to insufficient fine-grained supervision and strong bias towards understanding objects rather than temporal dynamics in current methods. To tackle these issues, we introduce a novel asymmetric contrastive objective for EgoHOI named EgoNCE++. For video-to-text loss, we enhance text supervision through the generation of negative captions by leveraging the in-context learning of LLMs to perform HOI-related word substitution. For text-to-video loss, we propose an object-centric positive video sampling strategy that aggregates video representations by the same nouns. Our extensive experiments demonstrate that EgoNCE++ significantly boosts open-vocabulary HOI recognition, multi-instance retrieval, and action recognition tasks across various egocentric models, with improvements of up to +26.55%. Our code is available at https://github.com/xuboshen/EgoNCEpp.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (61)
  1. Meta AI. Meta llama 3. https://github.com/meta-llama/llama3, 2024.
  2. Test of time: Instilling video-language models with a sense of time. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 2503–2516, 2023.
  3. Videocon: Robust video-language alignment via contrast captions. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024.
  4. VLMo: Unified vision-language pre-training with mixture-of-modality-experts. In Alice H. Oh, Alekh Agarwal, Danielle Belgrave, and Kyunghyun Cho, editors, Advances in Neural Information Processing Systems, 2022.
  5. Language models are few-shot learners. Advances in neural information processing systems, 33:1877–1901, 2020.
  6. Quo vadis, action recognition? a new model and the kinetics dataset. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pages 4724–4733, 2017.
  7. Opening the vocabulary of egocentric actions. Advances in Neural Information Processing Systems, 36, 2024.
  8. The epic-kitchens dataset: Collection, challenges and baselines. IEEE Transactions on Pattern Analysis and Machine Intelligence (TPAMI), 43(11):4125–4141, 2021.
  9. Imagenet: A large-scale hierarchical image database. In 2009 IEEE Conference on Computer Vision and Pattern Recognition, pages 248–255, 2009.
  10. The" something something" video database for learning and evaluating visual common sense. In Proceedings of the IEEE international conference on computer vision, pages 5842–5850, 2017.
  11. Ego4d: Around the world in 3,000 hours of egocentric video. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 18995–19012, 2022.
  12. Ego-exo4d: Understanding skilled human activity from first-and third-person perspectives. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024.
  13. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 16000–16009, 2022.
  14. LoRA: Low-rank adaptation of large language models. In International Conference on Learning Representations, 2022.
  15. Predicting gaze in egocentric video by learning task-dependent attention transition. In Proceedings of the European conference on computer vision (ECCV), pages 754–769, 2018.
  16. With a little help from my temporal context: Multimodal egocentric action recognition. In British Machine Vision Conference (BMVC), 2021.
  17. Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International conference on machine learning, pages 12888–12900. PMLR, 2022.
  18. Align before fuse: Vision and language representation learning with momentum distillation. Advances in neural information processing systems, 34:9694–9705, 2021.
  19. Ego-exo: Transferring visual representations from third-person to first-person videos. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6943–6953, 2021.
  20. In the eye of beholder: Joint learning of gaze and actions in first person video. In Proceedings of the European conference on computer vision (ECCV), pages 619–635, 2018.
  21. Egocentric video-language pretraining. Advances in Neural Information Processing Systems, 35:7575–7586, 2022.
  22. Roberta: A robustly optimized bert pretraining approach. ArXiv, abs/1907.11692, 2019.
  23. Clip4clip: An empirical study of clip for end to end video clip retrieval and captioning. Neurocomputing, 508:293–304, 2022.
  24. Egoschema: A diagnostic benchmark for very long-form video language understanding. Advances in Neural Information Processing Systems, 36, 2024.
  25. Something-else: Compositional action recognition with spatial-temporal interaction networks. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 1049–1059, 2020.
  26. Verbs in action: Improving verb understanding in video-language models. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 15579–15591, 2023.
  27. Embodiedgpt: Vision-language pre-training via embodied chain of thought. Advances in Neural Information Processing Systems, 36, 2024.
  28. Bleu: a method for automatic evaluation of machine translation. In Annual Meeting of the Association for Computational Linguistics, 2002.
  29. An outlook into the future of egocentric vision. arXiv preprint arXiv:2308.07123, 2023.
  30. What can a cook in italy teach a mechanic in india? action recognition generalisation over scenarios and locations. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13656–13666, 2023.
  31. Egovlpv2: Egocentric video-language pre-training with fusion in the backbone. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5285–5297, 2023.
  32. Learning transferable visual models from natural language supervision. In International conference on machine learning, pages 8748–8763. PMLR, 2021.
  33. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9, 2019.
  34. Exploring the limits of transfer learning with a unified text-to-text transformer. Journal of machine learning research, 21(140):1–67, 2020.
  35. Contrastive learning with hard negative samples. In International Conference on Learning Representations, 2021.
  36. Egocentric auditory attention localization in conversations. 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 14663–14674, 2023.
  37. Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter. ArXiv, abs/1910.01108, 2019.
  38. Assembly101: A large-scale multi-view video dataset for understanding procedural activities. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 21096–21106, 2022.
  39. Understanding human hands in contact at internet scale. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9869–9878, 2020.
  40. Actor and observer: Joint modeling of first and third-person videos. In proceedings of the IEEE conference on computer vision and pattern recognition, pages 7396–7404, 2018.
  41. Actor and observer: Joint modeling of first and third-person videos. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 7396–7404, 2018.
  42. Flava: A foundational language and vision alignment model. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 15638–15650, 2022.
  43. Lsta: Long short-term attention for egocentric action recognition. In Proceedings of the IEEE/CVF conference on computer vision and pattern recognition, pages 9954–9963, 2019.
  44. Ego-only: Egocentric action detection without exocentric transferring. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 5250–5261, 2023.
  45. Interactive prototype learning for egocentric action recognition. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 8168–8177, 2021.
  46. Vatex: A large-scale, high-quality multilingual dataset for video-and-language research. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 4581–4591, 2019.
  47. Paxion: Patching action knowledge in video-language foundation models. In Thirty-seventh Conference on Neural Information Processing Systems, 2023.
  48. Fine-grained action retrieval through multiple parts-of-speech embeddings. In Proceedings of the IEEE/CVF international conference on computer vision, pages 450–459, 2019.
  49. Rethinking spatiotemporal feature learning: Speed-accuracy trade-offs in video classification. In Proceedings of the European conference on computer vision (ECCV), pages 305–321, 2018.
  50. Pov: Prompt-oriented view-agnostic learning for egocentric hand-object interaction in the multi-view world. In Proceedings of the 31st ACM International Conference on Multimedia, pages 2807–2816, 2023.
  51. VideoCLIP: Contrastive pre-training for zero-shot video-text understanding. In Marie-Francine Moens, Xuanjing Huang, Lucia Specia, and Scott Wen-tau Yih, editors, Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 6787–6800, Online and Punta Cana, Dominican Republic, November 2021. Association for Computational Linguistics.
  52. Msr-vtt: A large video description dataset for bridging video and language. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 5288–5296, 2016.
  53. Learning fine-grained view-invariant representations from unpaired ego-exo videos via temporal alignment. Advances in Neural Information Processing Systems, 36, 2024.
  54. When and why vision-language models behave like bags-of-words, and what to do about it? In International Conference on Learning Representations, 2023.
  55. Socratic models: Composing zero-shot multimodal reasoning with language. In The Eleventh International Conference on Learning Representations, 2023.
  56. Multi-grained vision language pre-training: Aligning texts with visual concepts. In Kamalika Chaudhuri, Stefanie Jegelka, Le Song, Csaba Szepesvári, Gang Niu, and Sivan Sabato, editors, International Conference on Machine Learning, ICML 2022, 17-23 July 2022, Baltimore, Maryland, USA, volume 162 of Proceedings of Machine Learning Research, pages 25994–26009. PMLR, 2022.
  57. Helping hands: An object-aware ego-centric video recognition model. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 13901–13912, 2023.
  58. Fine-grained egocentric hand-object segmentation: Dataset, model, and applications. In European Conference on Computer Vision, pages 127–145. Springer, 2022.
  59. Learning video representations from large language models. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 6586–6597, 2023.
  60. Steve-eye: Equipping llm-based embodied agents with visual perception in open worlds. In The Twelfth International Conference on Learning Representations, 2023.
  61. Crossclr: Cross-modal contrastive learning for multi-modal video representations. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 1450–1459, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Boshen Xu (7 papers)
  2. Ziheng Wang (48 papers)
  3. Yang Du (24 papers)
  4. Sipeng Zheng (16 papers)
  5. Zhinan Song (1 paper)
  6. Qin Jin (94 papers)
Citations (1)
View on Semantic Scholar
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets