Peize Sun

papers

6,125

total citations

papers (17)

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

NEURIPS 2025arXiv

129

citations

Going Denser with Open-Vocabulary Part Segmentation

ICCV 2023arXiv

citations

Goku: Flow Based Video Generative Foundation Models

CVPR 2025arXiv

citations

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

NEURIPS 2025arXiv

citations

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

ICML 2024arXiv

citations

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

ICCV 2025arXiv

citations

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

ICLR 2025arXiv

citations

Watch Only Once: An End-to-End Video Action Detection Framework

ICCV 2021

citations

Domain-Invariant Disentangled Network for Generalizable Object Detection

ICCV 2021

citations

Peize Sun

papers (17)

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

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

DiffusionDet: Diffusion Model for Object Detection

PolarMask: Single Shot Instance Segmentation With Polar Representation

DetCo: Unsupervised Contrastive Learning for Object Detection

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

Language As Queries for Referring Video Object Segmentation

Towards Grand Unification of Object Tracking

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

Going Denser with Open-Vocabulary Part Segmentation

Goku: Flow Based Video Generative Foundation Models

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

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

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

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

Watch Only Once: An End-to-End Video Action Detection Framework

Domain-Invariant Disentangled Network for Generalizable Object Detection

papers (17)

ByteTrack: Multi-Object Tracking by Associating Every Detection Box

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

DiffusionDet: Diffusion Model for Object Detection

PolarMask: Single Shot Instance Segmentation With Polar Representation

DetCo: Unsupervised Contrastive Learning for Object Detection

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

Language As Queries for Referring Video Object Segmentation

Towards Grand Unification of Object Tracking

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

Going Denser with Open-Vocabulary Part Segmentation

Goku: Flow Based Video Generative Foundation Models

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

RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis

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

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

Watch Only Once: An End-to-End Video Action Detection Framework

Domain-Invariant Disentangled Network for Generalizable Object Detection