251 citations · 442 across the 40 of their papers we have counts for
40 papers
RASA: Disentangled Spatial-Motional Priors for Cross-Identity Character Animation
Zhen Xiao, Zhen Shen, Zhaofan Qiu +3
Cross-identity character animation aims to drive a target identity from a reference image to follow the motion of a source character from a driving video. The core challenge lies i…
HiDream-O1-Image: A Natively Unified Image Generative Foundation Model with Pixel-level Unified Transformer
Qi Cai, Jingwen Chen, Chengmin Gao +22
The evolution of visual generative models has long been constrained by fragmented architectures relying on disjoint text encoders and external VAEs. In this report, we present HiDr…
Region-Constraint In-Context Generation for Instructional Video Editing
Zhongwei Zhang, Fuchen Long, Wei Li +4
The In-context generation paradigm recently has demonstrated strong power in instructional image editing with both data efficiency and synthesis quality. Nevertheless, shaping such…
HiDream-I1: A High-Efficient Image Generative Foundation Model with Sparse Diffusion Transformer
Qi Cai, Jingwen Chen, Yang Chen +19
Recent advancements in image generative foundation models have prioritized quality improvements but often at the cost of increased computational complexity and inference latency. T…
MotionPro: A Precise Motion Controller for Image-to-Video Generation
Zhongwei Zhang, Fuchen Long, Zhaofan Qiu +4
Animating images with interactive motion control has garnered popularity for image-to-video (I2V) generation. Modern approaches typically rely on large Gaussian kernels to extend m…
Ouroboros-Diffusion: Exploring Consistent Content Generation in Tuning-free Long Video Diffusion
Jingyuan Chen, Fuchen Long, Jie An +4
The first-in-first-out (FIFO) video diffusion, built on a pre-trained text-to-video model, has recently emerged as an effective approach for tuning-free long video generation. This…
FreeEnhance: Tuning-Free Image Enhancement via Content-Consistent Noising-and-Denoising Process
Yang Luo, Yiheng Zhang, Zhaofan Qiu +4
The emergence of text-to-image generation models has led to the recognition that image enhancement, performed as post-processing, would significantly improve the visual quality of…
TRIP: Temporal Residual Learning with Image Noise Prior for Image-to-Video Diffusion Models
Zhongwei Zhang, Fuchen Long, Yingwei Pan +4
Recent advances in text-to-video generation have demonstrated the utility of powerful diffusion models. Nevertheless, the problem is not trivial when shaping diffusion models to an…
Learning Spatial Adaptation and Temporal Coherence in Diffusion Models for Video Super-Resolution
Zhikai Chen, Fuchen Long, Zhaofan Qiu +4
Diffusion models are just at a tipping point for image super-resolution task. Nevertheless, it is not trivial to capitalize on diffusion models for video super-resolution which nec…
VideoStudio: Generating Consistent-Content and Multi-Scene Videos
Fuchen Long, Zhaofan Qiu, Ting Yao +1
The recent innovations and breakthroughs in diffusion models have significantly expanded the possibilities of generating high-quality videos for the given prompts. Most existing wo…
Selective Volume Mixup for Video Action Recognition
Yi Tan, Zhaofan Qiu, Yanbin Hao +2
The recent advances in Convolutional Neural Networks (CNNs) and Vision Transformers have convincingly demonstrated high learning capability for video action recognition on large da…
Dynamic Temporal Filtering in Video Models
Fuchen Long, Zhaofan Qiu, Yingwei Pan +3
Video temporal dynamics is conventionally modeled with 3D spatial-temporal kernel or its factorized version comprised of 2D spatial kernel and 1D temporal kernel. The modeling powe…
SPE-Net: Boosting Point Cloud Analysis via Rotation Robustness Enhancement
Zhaofan Qiu, Yehao Li, Yu Wang +3
In this paper, we propose a novel deep architecture tailored for 3D point cloud applications, named as SPE-Net. The embedded ``Selective Position Encoding (SPE)'' procedure relies…
Explaining Cross-Domain Recognition with Interpretable Deep Classifier
Yiheng Zhang, Ting Yao, Zhaofan Qiu +1
The recent advances in deep learning predominantly construct models in their internal representations, and it is opaque to explain the rationale behind and decisions to human users…
Lightweight and Progressively-Scalable Networks for Semantic Segmentation
Yiheng Zhang, Ting Yao, Zhaofan Qiu +1
Multi-scale learning frameworks have been regarded as a capable class of models to boost semantic segmentation. The problem nevertheless is not trivial especially for the real-worl…
Bi-Calibration Networks for Weakly-Supervised Video Representation Learning
Fuchen Long, Ting Yao, Zhaofan Qiu +3
The leverage of large volumes of web videos paired with the searched queries or surrounding texts (e.g., title) offers an economic and extensible alternative to supervised video re…
Stand-Alone Inter-Frame Attention in Video Models
Fuchen Long, Zhaofan Qiu, Yingwei Pan +3
Motion, as the uniqueness of a video, has been critical to the development of video understanding models. Modern deep learning models leverage motion by either executing spatio-tem…
MLP-3D: A MLP-like 3D Architecture with Grouped Time Mixing
Zhaofan Qiu, Ting Yao, Chong-Wah Ngo +1
Convolutional Neural Networks (CNNs) have been regarded as the go-to models for visual recognition. More recently, convolution-free networks, based on multi-head self-attention (MS…
Silver-Bullet-3D at ManiSkill 2021: Learning-from-Demonstrations and Heuristic Rule-based Methods for Object Manipulation
Yingwei Pan, Yehao Li, Yiheng Zhang +5
This paper presents an overview and comparative analysis of our systems designed for the following two tracks in SAPIEN ManiSkill Challenge 2021: No Interaction Track: The No Inter…
Motion-Focused Contrastive Learning of Video Representations
Rui Li, Yiheng Zhang, Zhaofan Qiu +3
Motion, as the most distinct phenomenon in a video to involve the changes over time, has been unique and critical to the development of video representation learning. In this paper…
Representing Videos as Discriminative Sub-graphs for Action Recognition
Dong Li, Zhaofan Qiu, Yingwei Pan +3
Human actions are typically of combinatorial structures or patterns, i.e., subjects, objects, plus spatio-temporal interactions in between. Discovering such structures is therefore…
Boosting Video Representation Learning with Multi-Faceted Integration
Zhaofan Qiu, Ting Yao, Chong-Wah Ngo +3
Video content is multifaceted, consisting of objects, scenes, interactions or actions. The existing datasets mostly label only one of the facets for model training, resulting in th…
Condensing a Sequence to One Informative Frame for Video Recognition
Zhaofan Qiu, Ting Yao, Yan Shu +2
Video is complex due to large variations in motion and rich content in fine-grained visual details. Abstracting useful information from such information-intensive media requires ex…
Optimization Planning for 3D ConvNets
Zhaofan Qiu, Ting Yao, Chong-Wah Ngo +1
It is not trivial to optimally learn a 3D Convolutional Neural Networks (3D ConvNets) due to high complexity and various options of the training scheme. The most common hand-tuning…