papers

Publications (35)

cs.CV2022

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

Yifu Zhang, Peize Sun, Yi Jiang +6

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects in videos. Most methods obtain identities by associating detection boxes whose scores are hi…

cs.CV2019

Double Anchor R-CNN for Human Detection in a Crowd

Kevin Zhang, Feng Xiong, Peize Sun +3

Detecting human in a crowd is a challenging problem due to the uncertainties of occlusion patterns. In this paper, we propose to handle the crowd occlusion problem in human detecti…

cs.CV2023

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…

cs.CV2019

TextSR: Content-Aware Text Super-Resolution Guided by Recognition

Wenjia Wang, Enze Xie, Peize Sun +4

Scene text recognition has witnessed rapid development with the advance of convolutional neural networks. Nonetheless, most of the previous methods may not work well in recognizing…

cs.CV2020

PolarMask: Single Shot Instance Segmentation with Polar Representation

Enze Xie, Peize Sun, Xiaoge Song +4

In this paper, we introduce an anchor-box free and single shot instance segmentation method, which is conceptually simple, fully convolutional and can be used as a mask prediction…

cs.CV2023

Going Denser with Open-Vocabulary Part Segmentation

Peize Sun, Shoufa Chen, Chenchen Zhu +4

Object detection has been expanded from a limited number of categories to open vocabulary. Moving forward, a complete intelligent vision system requires understanding more fine-gra…

cs.CV2021

Towards High-Quality Temporal Action Detection with Sparse Proposals

Jiannan Wu, Peize Sun, Shoufa Chen +4

Temporal Action Detection (TAD) is an essential and challenging topic in video understanding, aiming to localize the temporal segments containing human action instances and predict…

cs.CV2022

DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion

Peize Sun, Jinkun Cao, Yi Jiang +4

A typical pipeline for multi-object tracking (MOT) is to use a detector for object localization, and following re-identification (re-ID) for object association. This pipeline is pa…

cs.CV2023

Semantic-SAM: Segment and Recognize Anything at Any Granularity

Feng Li, Hao Zhang, Peize Sun +6

In this paper, we introduce Semantic-SAM, a universal image segmentation model to enable segment and recognize anything at any desired granularity. Our model offers two key advanta…

cs.CV2022

Learning Object-Language Alignments for Open-Vocabulary Object Detection

Chuang Lin, Peize Sun, Yi Jiang +5

Existing object detection methods are bounded in a fixed-set vocabulary by costly labeled data. When dealing with novel categories, the model has to be retrained with more bounding…

cs.CV2026

OmniGen-AR: AutoRegressive Any-to-Image Generation

Junke Wang, Xun Wang, Qiushan Guo +4

Autoregressive (AR) models have demonstrated strong potential in visual generation, offering superior performance with simple architectures and optimization objectives. However, ex…

cs.CV2025

Token-Shuffle: Towards High-Resolution Image Generation with Autoregressive Models

Xu Ma, Peize Sun, Haoyu Ma +22

Autoregressive (AR) models, long dominant in language generation, are increasingly applied to image synthesis but are often considered less competitive than Diffusion-based models.…

cs.CV2022

Objects in Semantic Topology

Shuo Yang, Peize Sun, Yi Jiang +6

A more realistic object detection paradigm, Open-World Object Detection, has arisen increasing research interests in the community recently. A qualified open-world object detector…

cs.CV2024

IDA-VLM: Towards Movie Understanding via ID-Aware Large Vision-Language Model

Yatai Ji, Shilong Zhang, Jie Wu +6

The rapid advancement of Large Vision-Language models (LVLMs) has demonstrated a spectrum of emergent capabilities. Nevertheless, current models only focus on the visual content of…

cs.CV2025

GPT4RoI: Instruction Tuning Large Language Model on Region-of-Interest

Shilong Zhang, Peize Sun, Shoufa Chen +6

Visual instruction tuning large language model(LLM) on image-text pairs has achieved general-purpose vision-language abilities. However, the lack of region-text pairs limits their…

cs.CV2025

PixelFlow: Pixel-Space Generative Models with Flow

Shoufa Chen, Chongjian Ge, Shilong Zhang +2

We present PixelFlow, a family of image generation models that operate directly in the raw pixel space, in contrast to the predominant latent-space models. This approach simplifies…

cs.CV2025

Perception Encoder: The best visual embeddings are not at the output of the network

Daniel Bolya, Po-Yao Huang, Peize Sun +15

We introduce Perception Encoder (PE), a state-of-the-art vision encoder for image and video understanding trained via simple vision-language learning. Traditionally, vision encoder…

cs.CV2024

Autoregressive Model Beats Diffusion: Llama for Scalable Image Generation

Peize Sun, Yi Jiang, Shoufa Chen +4

We introduce LlamaGen, a new family of image generation models that apply original ``next-token prediction'' paradigm of large language models to visual generation domain. It is an…

cs.CV2024

Toward Guidance-Free AR Visual Generation via Condition Contrastive Alignment

Huayu Chen, Hang Su, Peize Sun +1

Classifier-Free Guidance (CFG) is a critical technique for enhancing the sample quality of visual generative models. However, in autoregressive (AR) multi-modal generation, CFG int…

cs.CV2021

What Makes for End-to-End Object Detection?

Peize Sun, Yi Jiang, Enze Xie +4

Object detection has recently achieved a breakthrough for removing the last one non-differentiable component in the pipeline, Non-Maximum Suppression (NMS), and building up an end-…

cs.CV2025

ControlAR: Controllable Image Generation with Autoregressive Models

Zongming Li, Tianheng Cheng, Shoufa Chen +6

Autoregressive (AR) models have reformulated image generation as next-token prediction, demonstrating remarkable potential and emerging as strong competitors to diffusion models. H…

cs.RO2024

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

Yao Mu, Junting Chen, Qinglong Zhang +16

Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI. Despite successe…

cs.CV2022

Towards Grand Unification of Object Tracking

Bin Yan, Yi Jiang, Peize Sun +4

We present a unified method, termed Unicorn, that can simultaneously solve four tracking problems (SOT, MOT, VOS, MOTS) with a single network using the same model parameters. Due t…

cs.CV2026

SAM 3: Segment Anything with Concepts

Nicolas Carion, Laura Gustafson, Yuan-Ting Hu +35

We present Segment Anything Model (SAM) 3, a unified model that detects, segments, and tracks objects in images and videos based on concept prompts, which we define as either short…

cs.CV2021

Sparse R-CNN: End-to-End Object Detection with Learnable Proposals

Peize Sun, Rufeng Zhang, Yi Jiang +8

We present Sparse R-CNN, a purely sparse method for object detection in images. Existing works on object detection heavily rely on dense object candidates, such as anchor boxes…

cs.CV2023

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

Yifu Zhang, Xinggang Wang, Xiaoqing Ye +6

Multi-object tracking (MOT) aims at estimating bounding boxes and identities of objects across video frames. Detection boxes serve as the basis of both 2D and 3D MOT. The inevitabl…

cs.CV2021

Segmenting Transparent Object in the Wild with Transformer

Enze Xie, Wenjia Wang, Wenhai Wang +4

This work presents a new fine-grained transparent object segmentation dataset, termed Trans10K-v2, extending Trans10K-v1, the first large-scale transparent object segmentation data…

cs.CV2025

PerceptionLM: Open-Access Data and Models for Detailed Visual Understanding

Jang Hyun Cho, Andrea Madotto, Effrosyni Mavroudi +26

Vision-language models are integral to computer vision research, yet many high-performing models remain closed-source, obscuring their data, design and training recipe. The researc…

cs.CV2023

DiffusionDet: Diffusion Model for Object Detection

Shoufa Chen, Peize Sun, Yibing Song +1

We propose DiffusionDet, a new framework that formulates object detection as a denoising diffusion process from noisy boxes to object boxes. During the training stage, object boxes…

cs.CV2024

Prompt-A-Video: Prompt Your Video Diffusion Model via Preference-Aligned LLM

Yatai Ji, Jiacheng Zhang, Jie Wu +9

Text-to-video models have made remarkable advancements through optimization on high-quality text-video pairs, where the textual prompts play a pivotal role in determining quality o…

cs.CV2022

Language as Queries for Referring Video Object Segmentation

Jiannan Wu, Yi Jiang, Peize Sun +2

Referring video object segmentation (R-VOS) is an emerging cross-modal task that aims to segment the target object referred by a language expression in all video frames. In this wo…

cs.CV2021

DetCo: Unsupervised Contrastive Learning for Object Detection

Enze Xie, Jian Ding, Wenhai Wang +5

Unsupervised contrastive learning achieves great success in learning image representations with CNN. Unlike most recent methods that focused on improving accuracy of image classifi…

cs.CV2026

FlashVideo: Flowing Fidelity to Detail for Efficient High-Resolution Video Generation

Shilong Zhang, Wenbo Li, Shoufa Chen +7

DiT models have achieved great success in text-to-video generation, leveraging their scalability in model capacity and data scale. High content and motion fidelity aligned with tex…

cs.CV2021

TransTrack: Multiple Object Tracking with Transformer

Peize Sun, Jinkun Cao, Yi Jiang +5

In this work, we propose TransTrack, a simple but efficient scheme to solve the multiple object tracking problems. TransTrack leverages the transformer architecture, which is an at…

cs.CV2025

Goku: Flow Based Video Generative Foundation Models

Shoufa Chen, Chongjian Ge, Yuqi Zhang +19

This paper introduces Goku, a state-of-the-art family of joint image-and-video generation models leveraging rectified flow Transformers to achieve industry-leading performance. We…