6 citations · 13 across the 9 of their papers we have counts for
10 papers · 1 filter
VideoRAE: Taming Video Foundation Models for Generative Modeling via Representation Autoencoders
Zhihao Xie, Junfeng Wu, Xinting Hu +2
Video generation models typically rely on 3D-VAEs trained for pixel-level reconstruction, whose latent spaces may underrepresent semantic structure. We introduce VideoRAE, a repres…
TokBench: Evaluating Your Visual Tokenizer before Visual Generation
Junfeng Wu, Dongliang Luo, Weizhi Zhao +6
In this work, we reveal the limitations of visual tokenizers and VAEs in preserving fine-grained features, and propose a benchmark to evaluate reconstruction performance for two ch…
UniTok: A Unified Tokenizer for Visual Generation and Understanding
Chuofan Ma, Yi Jiang, Junfeng Wu +5
Visual generative and understanding models typically rely on distinct tokenizers to process images, presenting a key challenge for unifying them within a single framework. Recent s…
Liquid: Language Models are Scalable and Unified Multi-modal Generators
Junfeng Wu, Yi Jiang, Chuofan Ma +5
We present Liquid, an auto-regressive generation paradigm that seamlessly integrates visual comprehension and generation by tokenizing images into discrete codes and learning these…
PartGLEE: A Foundation Model for Recognizing and Parsing Any Objects
Junyi Li, Junfeng Wu, Weizhi Zhao +2
We present PartGLEE, a part-level foundation model for locating and identifying both objects and parts in images. Through a unified framework, PartGLEE accomplishes detection, segm…
General Object Foundation Model for Images and Videos at Scale
Junfeng Wu, Yi Jiang, Qihao Liu +3
We present GLEE in this work, an object-level foundation model for locating and identifying objects in images and videos. Through a unified framework, GLEE accomplishes detection,…
InstMove: Instance Motion for Object-centric Video Segmentation
Qihao Liu, Junfeng Wu, Yi Jiang +3
Despite significant efforts, cutting-edge video segmentation methods still remain sensitive to occlusion and rapid movement, due to their reliance on the appearance of objects in t…
The Runner-up Solution for YouTube-VIS Long Video Challenge 2022
Junfeng Wu, Yi Jiang, Qihao Liu +2
This technical report describes our 2nd-place solution for the ECCV 2022 YouTube-VIS Long Video Challenge. We adopt the previously proposed online video instance segmentation metho…
In Defense of Online Models for Video Instance Segmentation
Junfeng Wu, Qihao Liu, Yi Jiang +3
In recent years, video instance segmentation (VIS) has been largely advanced by offline models, while online models gradually attracted less attention possibly due to their inferio…
SeqFormer: Sequential Transformer for Video Instance Segmentation
Junfeng Wu, Yi Jiang, Song Bai +2
In this work, we present SeqFormer for video instance segmentation. SeqFormer follows the principle of vision transformer that models instance relationships among video frames. Nev…