b'Xinggang Wang'

research

∙ 09/21/2023

TinyCLIP: CLIP Distillation via Affinity Mimicking and Weight Inheritance

In this paper, we propose a novel cross-modal distillation method, calle...

0 Kan Wu, et al. ∙

research

∙ 09/05/2023

TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction

Four-dimensional Digital Subtraction Angiography (4D DSA) plays a critic...

0 Zhenghong Zhou, et al. ∙

research

∙ 08/31/2023

TouchStone: Evaluating Vision-Language Models by Language Models

Large vision-language models (LVLMs) have recently witnessed rapid advan...

0 Shuai Bai, et al. ∙

research

∙ 08/10/2023

MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction

High-definition (HD) map provides abundant and precise static environmen...

0 Bencheng Liao, et al. ∙

research

∙ 06/27/2023

Symphonize 3D Semantic Scene Completion with Contextual Instance Queries

3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal ...

0 Haoyi Jiang, et al. ∙

research

∙ 06/23/2023

ProRes: Exploring Degradation-aware Visual Prompt for Universal Image Restoration

Image restoration aims to reconstruct degraded images, e.g., denoising o...

0 JiaQi Ma, et al. ∙

research

∙ 06/08/2023

SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth

Exploring robust and efficient association methods has always been an im...

0 Zelin Liu, et al. ∙

research

∙ 06/08/2023

Multi-level Multiple Instance Learning with Transformer for Whole Slide Image Classification

Whole slide image (WSI) refers to a type of high-resolution scanned tiss...

0 Ruijie Zhang, et al. ∙

research

∙ 06/07/2023

Matte Anything: Interactive Natural Image Matting with Segment Anything Models

Natural image matting algorithms aim to predict the transparency map (al...

0 Jingfeng Yao, et al. ∙

research

∙ 05/31/2023

GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition

Gait recognition is an emerging biological recognition technology that i...

0 Haijun Xiong, et al. ∙

research

∙ 05/24/2023

ViTMatte: Boosting Image Matting with Pretrained Plain Vision Transformers

Recently, plain vision Transformers (ViTs) have shown impressive perform...

0 Jingfeng Yao, et al. ∙

research

∙ 05/18/2023

ONE-PEACE: Exploring One General Representation Model Toward Unlimited Modalities

In this work, we explore a scalable way for building a general represent...

0 Peng Wang, et al. ∙

research

∙ 05/16/2023

A Range-Null Space Decomposition Approach for Fast and Flexible Spectral Compressive Imaging

We present RND-SCI, a novel framework for compressive hyperspectral imag...

0 Junyu Wang, et al. ∙

research

∙ 04/19/2023

VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene

High-definition (HD) map serves as the essential infrastructure of auton...

0 Shaoyu Chen, et al. ∙

research

∙ 04/19/2023

Post-Training Quantization for Object Detection

Efficient inference for object detection networks is a major challenge o...

0 Lin Niu, et al. ∙

research

∙ 04/03/2023

WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation

This paper explores the properties of the plain Vision Transformer (ViT)...

0 Lianghui Zhu, et al. ∙

research

∙ 04/03/2023

RPTQ: Reorder-based Post-training Quantization for Large Language Models

Large-scale language models (LLMs) have demonstrated outstanding perform...

0 Zhihang Yuan, et al. ∙

research

∙ 03/30/2023

MobileInst: Video Instance Segmentation on the Mobile

Although recent approaches aiming for video instance segmentation have a...

0 Renhong Zhang, et al. ∙

research

∙ 03/28/2023

OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation

Open-world instance segmentation has recently gained significant popular...

0 Cheng Wang, et al. ∙

research

∙ 03/27/2023

Generalizable Neural Voxels for Fast Human Radiance Fields

Rendering moving human bodies at free viewpoints only from a monocular v...

0 Taoran Yi, et al. ∙

research

∙ 03/27/2023

ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box

Multi-object tracking (MOT) aims at estimating bounding boxes and identi...

0 Yifu Zhang, et al. ∙

research

∙ 03/23/2023

Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance

Post-training quantization (PTQ) is a popular method for compressing dee...

0 Zhihang Yuan, et al. ∙

research

∙ 03/21/2023

VAD: Vectorized Scene Representation for Efficient Autonomous Driving

Autonomous driving requires a comprehensive understanding of the surroun...

0 Bo Jiang, et al. ∙

research

∙ 03/20/2023

EVA-02: A Visual Representation for Neon Genesis

We launch EVA-02, a next-generation Transformer-based visual representat...

0 Yuxin Fang, et al. ∙

research

∙ 03/15/2023

Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction

Online lane graph construction is a promising but challenging task in au...

0 Bencheng Liao, et al. ∙

research

∙ 02/02/2023

Boosting Low-Data Instance Segmentation by Unsupervised Pre-training with Saliency Prompt

Recently, inspired by DETR variants, query-based end-to-end instance seg...

0 Hao Li, et al. ∙

research

∙ 01/26/2023

Graph Contrastive Learning for Skeleton-based Action Recognition

In the field of skeleton-based action recognition, current top-performin...

0 Xiaohu Huang, et al. ∙

research

∙ 01/24/2023

A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction

We present a simple, efficient, and scalable unfolding network, SAUNet, ...

0 Junyu Wang, et al. ∙

research

∙ 01/17/2023

Masked Visual Reconstruction in Language Semantic Space

Both masked image modeling (MIM) and natural language supervision have f...

8 Shusheng Yang, et al. ∙

research

∙ 12/14/2022

PD-Quant: Post-Training Quantization based on Prediction Difference Metric

As a neural network compression technique, post-training quantization (P...

0 Jiawei Liu, et al. ∙

research

∙ 12/05/2022

Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction

Motion prediction is highly relevant to the perception of dynamic object...

0 Bo Jiang, et al. ∙

research

∙ 11/14/2022

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale

We launch EVA, a vision-centric foundation model to explore the limits o...

0 Yuxin Fang, et al. ∙

research

∙ 10/11/2022

BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation

Labeling objects with pixel-wise segmentation requires a huge amount of ...

8 Tianheng Cheng, et al. ∙

research

∙ 08/30/2022

MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction

We present MapTR, a structured end-to-end framework for efficient online...

3 Bencheng Liao, et al. ∙

research

∙ 08/07/2022

Robust Multi-Object Tracking by Marginal Inference

Multi-object tracking in videos requires to solve a fundamental problem ...

0 Yifu Zhang, et al. ∙

research

∙ 07/20/2022

AiATrack: Attention in Attention for Transformer Visual Tracking

Transformer trackers have achieved impressive advancements recently, whe...

0 Shenyuan Gao, et al. ∙

research

∙ 07/05/2022

Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation

In this work, we propose PolarBEV for vision-based uneven BEV representa...

2 Zhi Liu, et al. ∙

research

∙ 06/22/2022

Polar Parametrization for Vision-based Surround-View 3D Detection

3D detection based on surround-view camera system is a critical techniqu...

3 Shaoyu Chen, et al. ∙

research

∙ 06/13/2022

Featurized Query R-CNN

The query mechanism introduced in the DETR method is changing the paradi...

8 Wenqiang Zhang, et al. ∙

research

∙ 06/09/2022

Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer

Learning Bird's Eye View (BEV) representation from surrounding-view came...

13 Shaoyu Chen, et al. ∙

research

∙ 05/30/2022

Fast Dynamic Radiance Fields with Time-Aware Neural Voxels

Neural radiance fields (NeRF) have shown great success in modeling 3D sc...

0 Jiemin Fang, et al. ∙

research

∙ 04/18/2022

Temporally Efficient Vision Transformer for Video Instance Segmentation

Recently vision transformer has achieved tremendous success on image-lev...

0 Shusheng Yang, et al. ∙

research

∙ 04/12/2022

TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation

Although vision transformers (ViTs) have achieved great success in compu...

3 Wenqiang Zhang, et al. ∙

research

∙ 04/06/2022

Unleashing Vanilla Vision Transformer with Masked Image Modeling for Object Detection

We present an approach to efficiently and effectively adapt a masked ima...

14 Yuxin Fang, et al. ∙

research

∙ 03/24/2022

AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception

Studying the inherent symmetry of data is of great importance in machine...

1 Shaoyu Chen, et al. ∙

research

∙ 03/24/2022

Sparse Instance Activation for Real-Time Instance Segmentation

In this paper, we propose a conceptually novel, efficient, and fully con...

15 Tianheng Cheng, et al. ∙

research

∙ 02/07/2022

Corrupted Image Modeling for Self-Supervised Visual Pre-Training

We introduce Corrupted Image Modeling (CIM) for self-supervised visual p...

0 Yuxin Fang, et al. ∙

research

∙ 11/30/2021

NeuSample: Neural Sample Field for Efficient View Synthesis

Neural radiance fields (NeRF) have shown great potentials in representin...

0 Jiemin Fang, et al. ∙

research

∙ 11/15/2021

Occluded Video Instance Segmentation: Dataset and ICCV 2021 Challenge

Although deep learning methods have achieved advanced video object recog...

12 Jiyang Qi, et al. ∙

research

∙ 10/13/2021

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Multi-object tracking (MOT) aims at estimating bounding boxes and identi...

0 Yifu Zhang, et al. ∙

Xinggang Wang

Featured Co-authors