18 citations · 36 across the 10 of their papers we have counts for
10 papers
Adaptive Begin-of-Video Tokens for Autoregressive Video Diffusion Models
Tianle Cheng, Zeyan Zhang, Kaifeng Gao +1
Recent advancements in diffusion-based video generation have produced impressive and high-fidelity short videos. To extend these successes to generate coherent long videos, most vi…
Generalized Visual Relation Detection with Diffusion Models
Kaifeng Gao, Siqi Chen, Hanwang Zhang +3
Visual relation detection (VRD) aims to identify relationships (or interactions) between object pairs in an image. Although recent VRD models have achieved impressive performance,…
Towards Better Alignment: Training Diffusion Models with Reinforcement Learning Against Sparse Rewards
Zijing Hu, Fengda Zhang, Long Chen +6
Diffusion models have achieved remarkable success in text-to-image generation. However, their practical applications are hindered by the misalignment between generated images and c…
Ca2-VDM: Efficient Autoregressive Video Diffusion Model with Causal Generation and Cache Sharing
Kaifeng Gao, Jiaxin Shi, Hanwang Zhang +3
With the advance of diffusion models, today's video generation has achieved impressive quality. To extend the generation length and facilitate real-world applications, a majority o…
ViD-GPT: Introducing GPT-style Autoregressive Generation in Video Diffusion Models
Kaifeng Gao, Jiaxin Shi, Hanwang Zhang +2
With the advance of diffusion models, today's video generation has achieved impressive quality. But generating temporal consistent long videos is still challenging. A majority of v…
Triple Correlations-Guided Label Supplementation for Unbiased Video Scene Graph Generation
Wenqing Wang, Kaifeng Gao, Yawei Luo +5
Video-based scene graph generation (VidSGG) is an approach that aims to represent video content in a dynamic graph by identifying visual entities and their relationships. Due to th…
Compositional Prompt Tuning with Motion Cues for Open-vocabulary Video Relation Detection
Kaifeng Gao, Long Chen, Hanwang Zhang +2
Prompt tuning with large-scale pretrained vision-language models empowers open-vocabulary predictions trained on limited base categories, e.g., object classification and detection.…
Rethinking Multi-Modal Alignment in Video Question Answering from Feature and Sample Perspectives
Shaoning Xiao, Long Chen, Kaifeng Gao +4
Reasoning about causal and temporal event relations in videos is a new destination of Video Question Answering (VideoQA).The major stumbling block to achieve this purpose is the se…
Classification-Then-Grounding: Reformulating Video Scene Graphs as Temporal Bipartite Graphs
Kaifeng Gao, Long Chen, Yulei Niu +2
Today's VidSGG models are all proposal-based methods, i.e., they first generate numerous paired subject-object snippets as proposals, and then conduct predicate classification for…
Video Relation Detection via Tracklet based Visual Transformer
Kaifeng Gao, Long Chen, Yifeng Huang +1
Video Visual Relation Detection (VidVRD), has received significant attention of our community over recent years. In this paper, we apply the state-of-the-art video object tracklet…