128 citations · 757 across the 38 of their papers we have counts for
8 papers · 1 filter
InternVideo: General Video Foundation Models via Generative and Discriminative Learning
Yi Wang, Kunchang Li, Yizhuo Li +14
The foundation models have recently shown excellent performance on a variety of downstream tasks in computer vision. However, most existing vision foundation models simply focus on…
UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer
Kunchang Li, Yali Wang, Yinan He +4
Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term v…
InternVideo-Ego4D: A Pack of Champion Solutions to Ego4D Challenges
Guo Chen, Sen Xing, Zhe Chen +18
In this report, we present our champion solutions to five tracks at Ego4D challenge. We leverage our developed InternVideo, a video foundation model, for five Ego4D tasks, includin…
Tip-Adapter: Training-free Adaption of CLIP for Few-shot Classification
Renrui Zhang, Zhang Wei, Rongyao Fang +5
Contrastive Vision-Language Pre-training, known as CLIP, has provided a new paradigm for learning visual representations using large-scale image-text pairs. It shows impressive per…
MVP: Robust Multi-View Practice for Driving Action Localization
Jingjie Shang, Kunchang Li, Kaibin Tian +2
Distracted driving causes thousands of deaths per year, and how to apply deep-learning methods to prevent these tragedies has become a crucial problem. In Track3 of the 6th AI City…
You Only Need 90K Parameters to Adapt Light: A Light Weight Transformer for Image Enhancement and Exposure Correction
Ziteng Cui, Kunchang Li, Lin Gu +5
Challenging illumination conditions (low-light, under-exposure and over-exposure) in the real world not only cast an unpleasant visual appearance but also taint the computer vision…
UniFormer: Unified Transformer for Efficient Spatiotemporal Representation Learning
Kunchang Li, Yali Wang, Peng Gao +4
It is a challenging task to learn rich and multi-scale spatiotemporal semantics from high-dimensional videos, due to large local redundancy and complex global dependency between vi…
UniFormer: Unifying Convolution and Self-attention for Visual Recognition
Kunchang Li, Yali Wang, Junhao Zhang +5
It is a challenging task to learn discriminative representation from images and videos, due to large local redundancy and complex global dependency in these visual data. Convolutio…