349 citations · 1.3k across the 44 of their papers we have counts for
43 papers · 1 filter
Flash-VStream: Efficient Real-Time Understanding for Long Video Streams
Haoji Zhang, Yiqin Wang, Yansong Tang +3
Benefiting from the advances in large language models and cross-modal alignment, existing multimodal large language models have achieved prominent performance in image and short vi…
VideoWorld: Exploring Knowledge Learning from Unlabeled Videos
Zhongwei Ren, Yunchao Wei, Xun Guo +4
This work explores whether a deep generative model can learn complex knowledge solely from visual input, in contrast to the prevalent focus on text-based models like large language…
Hierarchical Memory for Long Video QA
Yiqin Wang, Haoji Zhang, Yansong Tang +4
This paper describes our champion solution to the LOVEU Challenge @ CVPR'24, Track 1 (Long Video VQA). Processing long sequences of visual tokens is computationally expensive and m…
Flash-VStream: Memory-Based Real-Time Understanding for Long Video Streams
Haoji Zhang, Yiqin Wang, Yansong Tang +4
Benefiting from the advancements in large language models and cross-modal alignment, existing multi-modal video understanding methods have achieved prominent performance in offline…
Video Recognition in Portrait Mode
Mingfei Han, Linjie Yang, Xiaojie Jin +3
The creation of new datasets often presents new challenges for video recognition and can inspire novel ideas while addressing these challenges. While existing datasets mainly compr…
Vista-LLaMA: Reducing Hallucination in Video Language Models via Equal Distance to Visual Tokens
Fan Ma, Xiaojie Jin, Heng Wang +3
Recent advances in large video-language models have displayed promising outcomes in video comprehension. Current approaches straightforwardly convert video into language tokens and…
PixelLM: Pixel Reasoning with Large Multimodal Model
Zhongwei Ren, Zhicheng Huang, Yunchao Wei +4
While large multimodal models (LMMs) have achieved remarkable progress, generating pixel-level masks for image reasoning tasks involving multiple open-world targets remains a chall…
Selective Feature Adapter for Dense Vision Transformers
Xueqing Deng, Qi Fan, Xiaojie Jin +2
Fine-tuning pre-trained transformer models, e.g., Swin Transformer, are successful in numerous downstream for dense prediction vision tasks. However, one major issue is the cost/st…
Realistic Full-Body Tracking from Sparse Observations via Joint-Level Modeling
Xiaozheng Zheng, Zhuo Su, Chao Wen +2
To bridge the physical and virtual worlds for rapidly developed VR/AR applications, the ability to realistically drive 3D full-body avatars is of great significance. Although real-…
COSA: Concatenated Sample Pretrained Vision-Language Foundation Model
Sihan Chen, Xingjian He, Handong Li +3
Due to the limited scale and quality of video-text training corpus, most vision-language foundation models employ image-text datasets for pretraining and primarily focus on modelin…
Delving Deeper into Data Scaling in Masked Image Modeling
Cheng-Ze Lu, Xiaojie Jin, Qibin Hou +3
Understanding whether self-supervised learning methods can scale with unlimited data is crucial for training large-scale models. In this work, we conduct an empirical study on the…
VLAB: Enhancing Video Language Pre-training by Feature Adapting and Blending
Xingjian He, Sihan Chen, Fan Ma +7
Large-scale image-text contrastive pre-training models, such as CLIP, have been demonstrated to effectively learn high-quality multimodal representations. However, there is limited…
Temporal Perceiving Video-Language Pre-training
Fan Ma, Xiaojie Jin, Heng Wang +4
Video-Language Pre-training models have recently significantly improved various multi-modal downstream tasks. Previous dominant works mainly adopt contrastive learning to achieve g…
CMAE-V: Contrastive Masked Autoencoders for Video Action Recognition
Cheng-Ze Lu, Xiaojie Jin, Zhicheng Huang +3
Contrastive Masked Autoencoder (CMAE), as a new self-supervised framework, has shown its potential of learning expressive feature representations in visual image recognition. This…
Revisiting Training-free NAS Metrics: An Efficient Training-based Method
Taojiannan Yang, Linjie Yang, Xiaojie Jin +1
Recent neural architecture search (NAS) works proposed training-free metrics to rank networks which largely reduced the search cost in NAS. In this paper, we revisit these training…
OSIC: A New One-Stage Image Captioner Coined
Bo Wang, Zhao Zhang, Mingbo Zhao +3
Mainstream image caption models are usually two-stage captioners, i.e., calculating object features by pre-trained detector, and feeding them into a language model to generate text…
Noise Self-Regression: A New Learning Paradigm to Enhance Low-Light Images Without Task-Related Data
Zhao Zhang, Suiyi Zhao, Xiaojie Jin +4
Deep learning-based low-light image enhancement (LLIE) is a task of leveraging deep neural networks to enhance the image illumination while keeping the image content unchanged. Fro…
Exploring Domain Incremental Video Highlights Detection with the LiveFood Benchmark
Sen Pei, Shixiong Xu, Xiaojie Jin
Video highlights detection (VHD) is an active research field in computer vision, aiming to locate the most user-appealing clips given raw video inputs. However, most VHD methods ar…
AutoTransition: Learning to Recommend Video Transition Effects
Yaojie Shen, Libo Zhang, Kai Xu +1
Video transition effects are widely used in video editing to connect shots for creating cohesive and visually appealing videos. However, it is challenging for non-professionals to…
Contrastive Masked Autoencoders are Stronger Vision Learners
Zhicheng Huang, Xiaojie Jin, Chengze Lu +5
Masked image modeling (MIM) has achieved promising results on various vision tasks. However, the limited discriminability of learned representation manifests there is still plenty…
Video Salient Object Detection via Contrastive Features and Attention Modules
Yi-Wen Chen, Xiaojie Jin, Xiaohui Shen +1
Video salient object detection aims to find the most visually distinctive objects in a video. To explore the temporal dependencies, existing methods usually resort to recurrent neu…
HR-NAS: Searching Efficient High-Resolution Neural Architectures with Lightweight Transformers
Mingyu Ding, Xiaochen Lian, Linjie Yang +4
High-resolution representations (HR) are essential for dense prediction tasks such as segmentation, detection, and pose estimation. Learning HR representations is typically ignored…
Refiner: Refining Self-attention for Vision Transformers
Daquan Zhou, Yujun Shi, Bingyi Kang +6
Vision Transformers (ViTs) have shown competitive accuracy in image classification tasks compared with CNNs. Yet, they generally require much more data for model pre-training. Most…
DeepViT: Towards Deeper Vision Transformer
Daquan Zhou, Bingyi Kang, Xiaojie Jin +5
Vision transformers (ViTs) have been successfully applied in image classification tasks recently. In this paper, we show that, unlike convolution neural networks (CNNs)that can be…