502 citations · 1.4k across the 190 of their papers we have counts for
39 papers · 1 filter
Forgery-aware Adaptive Transformer for Generalizable Synthetic Image Detection
Huan Liu, Zichang Tan, Chuangchuang Tan +3
In this paper, we study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods, e.g., GANs and diffusion models. Cu…
Noisy Correspondence Learning with Self-Reinforcing Errors Mitigation
Zhuohang Dang, Minnan Luo, Chengyou Jia +3
Cross-modal retrieval relies on well-matched large-scale datasets that are laborious in practice. Recently, to alleviate expensive data collection, co-occurring pairs from the Inte…
Generating Action-conditioned Prompts for Open-vocabulary Video Action Recognition
Chengyou Jia, Minnan Luo, Xiaojun Chang +6
Exploring open-vocabulary video action recognition is a promising venture, which aims to recognize previously unseen actions within any arbitrary set of categories. Existing method…
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
Yahao Shi, Yanmin Wu, Chenming Wu +7
This paper presents a 3D Gaussian Inverse Rendering (GIR) method, employing 3D Gaussian representations to effectively factorize the scene into material properties, light, and geom…
GPT4Vis: What Can GPT-4 Do for Zero-shot Visual Recognition?
Wenhao Wu, Huanjin Yao, Mengxi Zhang +3
This paper does not present a novel method. Instead, it delves into an essential, yet must-know baseline in light of the latest advancements in Generative Artificial Intelligence (…
GP-NeRF: Generalized Perception NeRF for Context-Aware 3D Scene Understanding
Hao Li, Dingwen Zhang, Yalun Dai +5
Applying NeRF to downstream perception tasks for scene understanding and representation is becoming increasingly popular. Most existing methods treat semantic prediction as an addi…
Disentangled Representation Learning with Transmitted Information Bottleneck
Zhuohang Dang, Minnan Luo, Chengyou Jia +4
Encoding only the task-related information from the raw data, \ie, disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Al…
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
Junkun Yuan, Xinyu Zhang, Hao Zhou +12
Model pre-training is essential in human-centric perception. In this paper, we first introduce masked image modeling (MIM) as a pre-training approach for this task. Upon revisiting…
Accelerating Vision Transformers Based on Heterogeneous Attention Patterns
Deli Yu, Teng Xi, Jianwei Li +7
Recently, Vision Transformers (ViTs) have attracted a lot of attention in the field of computer vision. Generally, the powerful representative capacity of ViTs mainly benefits from…
Forward Flow for Novel View Synthesis of Dynamic Scenes
Xiang Guo, Jiadai Sun, Yuchao Dai +6
This paper proposes a neural radiance field (NeRF) approach for novel view synthesis of dynamic scenes using forward warping. Existing methods often adopt a static NeRF to represen…
VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation
Xin Li, Wenqing Chu, Ye Wu +7
In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using r…
Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification
Zhiyin Shao, Xinyu Zhang, Changxing Ding +2
The pre-training task is indispensable for the text-to-image person re-identification (T2I-ReID) task. However, there are two underlying inconsistencies between these two tasks tha…
What Can Simple Arithmetic Operations Do for Temporal Modeling?
Wenhao Wu, Yuxin Song, Zhun Sun +3
Temporal modeling plays a crucial role in understanding video content. To tackle this problem, previous studies built complicated temporal relations through time sequence thanks to…
Boosting Few-shot Action Recognition with Graph-guided Hybrid Matching
Jiazheng Xing, Mengmeng Wang, Yudi Ruan +6
Class prototype construction and matching are core aspects of few-shot action recognition. Previous methods mainly focus on designing spatiotemporal relation modeling modules or co…
Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation
Huan Liu, Qiang Chen, Zichang Tan +9
In this paper, we study the problem of end-to-end multi-person pose estimation. State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e.…
SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation
Chengyou Jia, Minnan Luo, Zhuohang Dang +4
Despite significant progress in Text-to-Image (T2I) generative models, even lengthy and complex text descriptions still struggle to convey detailed controls. In contrast, Layout-to…
MA-FSAR: Multimodal Adaptation of CLIP for Few-Shot Action Recognition
Jiazheng Xing, Chao Xu, Mengmeng Wang +5
Applying large-scale vision-language pre-trained models like CLIP to few-shot action recognition (FSAR) can significantly enhance both performance and efficiency. While several stu…
Enhancing Your Trained DETRs with Box Refinement
Yiqun Chen, Qiang Chen, Peize Sun +3
We present a conceptually simple, efficient, and general framework for localization problems in DETR-like models. We add plugins to well-trained models instead of inefficiently des…
CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation
Lizhao Liu, Zhuangwei Zhuang, Shangxin Huang +5
We study the task of weakly-supervised point cloud semantic segmentation with sparse annotations (e.g., less than 0.1% points are labeled), aiming to reduce the expensive cost of d…
Semi-DETR: Semi-Supervised Object Detection with Detection Transformers
Jiacheng Zhang, Xiangru Lin, Wei Zhang +6
We analyze the DETR-based framework on semi-supervised object detection (SSOD) and observe that (1) the one-to-one assignment strategy generates incorrect matching when the pseudo…
Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
Zhongwei Qiu, Qiansheng Yang, Jian Wang +7
One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network. Existing methods typically improve the quality of heatmaps by c…
Vision Transformer with Attention Map Hallucination and FFN Compaction
Haiyang Xu, Zhichao Zhou, Dongliang He +2
Vision Transformer(ViT) is now dominating many vision tasks. The drawback of quadratic complexity of its token-wise multi-head self-attention (MHSA), is extensively addressed via e…
ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images
Wenwen Yu, Chengquan Zhang, Haoyu Cao +24
Structured text extraction is one of the most valuable and challenging application directions in the field of Document AI. However, the scenarios of past benchmarks are limited, an…
Multi-Modal 3D Object Detection by Box Matching
Zhe Liu, Xiaoqing Ye, Zhikang Zou +5
Multi-modal 3D object detection has received growing attention as the information from different sensors like LiDAR and cameras are complementary. Most fusion methods for 3D detect…