UARK-AICV / Video_Representation

[Asilomar 2022] Contextual Explainable Video Representation: Human Perception-based Understanding

Contextual Explainable Video Representation: Human Perception-based Understanding

In this repo, we re-collect a series of our existing works on the contextual explainable video representation.

Our works on Temporal Action Proposals Generation are summarized as follows:

• Agent-Environment Network (AEN, published in ICASSP 2021):
  • Paper: https://ieeexplore.ieee.org/abstract/document/9415101/
  • ArXiv: https://arxiv.org/abs/2107.08323
• Agent-Aware Boundary Network (ABN, published in IEEE Access):
  • Paper: https://ieeexplore.ieee.org/abstract/document/9530693/
• Actors-Environment Interaction (AEI, published in BMVC 2021, Oral Session):
  • Paper: https://www.bmvc2021-virtualconference.com/assets/papers/1095.pdf
  • ArXiv: https://arxiv.org/abs/2110.11474
  • Source code: https://github.com/UARK-AICV/TAPG-AgentEnvInteration.git
• Actors-Objects-Environment Network (AOE-Net, published in International Journal of Computer Vision):
  • Paper: https://link.springer.com/article/10.1007/s11263-022-01702-9
  • ArXiv: https://arxiv.org/abs/2210.02578
  • Source code: https://github.com/UARK-AICV/AOE-Net

Our works on Video Paragraph Captioning are summarized as follows:

• Vision-Language with Contrastive Learning for Coherent Video Paragraph Captioning (VLCap, published in ICIP 2022):
  • Paper: https://ieeexplore.ieee.org/abstract/document/9897766
  • ArXiv: https://arxiv.org/abs/2206.12972
  • Source code: https://github.com/UARK-AICV/VLCAP
• VLTinT: Visual-Linguistic Transformer-in-Transformer for Coherent Video Paragraph Captioning (VlLTinT, published in AAAI 2023):
  • ArXiv: https://arxiv.org/abs/2211.15103
  • Source code: https://github.com/UARK-AICV/VLTinT