305 citations · 813 across the 36 of their papers we have counts for
38 papers · 1 filter
QK-Edit: Revisiting Attention-based Injection in MM-DiT for Image and Video Editing
Tiancheng Shen, Zilong Huang, Xiangtai Li +6
Multimodal Diffusion Transformers (MM-DiTs) have recently emerged as a powerful framework for unified text-vision synthesis, surpassing traditional U-Net architectures in generativ…
Primitive-Driven Compositional Forensic Visual Prompting for Open-World Face Anti-Spoofing
Fangling Jiang, Qi Li, Bing Liu +4
Open-world face anti-spoofing must address both covariate and semantic shifts: source and target domains differ in imaging conditions, while target domains contain diverse attack t…
SeeSE3: Emergence of 3D Space in Vision Features
Caroline Chen, Sayna Ebrahimi, Fedor Kitashov +4
In this paper, we ask whether vision foundation models construct representations that reflect the intrinsic properties of 3D Euclidean space. Unlike previous works that probe 3D aw…
Beyond Random Sampling: Distribution-Aware Alignment for Semi-Supervised Medical Image Segmentation
Weihao Yan, Yeqiang Qian, Yi Dong +1
Precise medical image segmentation is crucial for clinical diagnosis and treatment planning, yet relies heavily on expensive expert annotations. Semi-supervised medical image segme…
Interactive Multi-Head Self-Attention with Linear Complexity
Hankyul Kang, Ming-Hsuan Yang, Jongbin Ryu
We propose an efficient interactive method for multi-head self-attention via decomposition. For existing methods using multi-head self-attention, the attention operation of each he…
PromptRR: Diffusion Models as Prompt Generators for Single Image Reflection Removal
Tao Wang, Wanglong Lu, Kaihao Zhang +2
Existing single image reflection removal (SIRR) methods using deep learning tend to miss key low-frequency (LF) and high-frequency (HF) differences in images, affecting their effec…
Structured Video-Language Modeling with Temporal Grouping and Spatial Grounding
Yuanhao Xiong, Long Zhao, Boqing Gong +5
Existing video-language pre-training methods primarily focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grai…
InfiniCity: Infinite-Scale City Synthesis
Chieh Hubert Lin, Hsin-Ying Lee, Willi Menapace +4
Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noi…
MAGVIT: Masked Generative Video Transformer
Lijun Yu, Yong Cheng, Kihyuk Sohn +8
We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model. We introduce a 3D tokenizer to quantize a video into spat…
FlowNAS: Neural Architecture Search for Optical Flow Estimation
Zhiwei Lin, Tingting Liang, Taihong Xiao +3
Existing optical flow estimators usually employ the network architectures typically designed for image classification as the encoder to extract per-pixel features. However, due to…
Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features
Chieh Hubert Lin, Hsin-Ying Lee, Hung-Yu Tseng +2
Recent studies show that paddings in convolutional neural networks encode absolute position information which can negatively affect the model performance for certain tasks. However…
Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing
Hsin-Ping Huang, Deqing Sun, Yaojie Liu +5
While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired…
V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer
Runsheng Xu, Hao Xiang, Zhengzhong Tu +3
In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles. We present a robust coopera…
Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text
Qing Li, Boqing Gong, Yin Cui +4
In this paper, we explore the possibility of building a unified foundation model that can be adapted to both vision-only and text-only tasks. Starting from BERT and ViT, we design…
An Informative Tracking Benchmark
Xin Li, Qiao Liu, Wenjie Pei +4
Along with the rapid progress of visual tracking, existing benchmarks become less informative due to redundancy of samples and weak discrimination between current trackers, making…
Exploring Temporal Granularity in Self-Supervised Video Representation Learning
Rui Qian, Yeqing Li, Liangzhe Yuan +7
This work presents a self-supervised learning framework named TeG to explore Temporal Granularity in learning video representations. In TeG, we sample a long clip from a video and…
Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision
Liangzhe Yuan, Rui Qian, Yin Cui +5
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views. While being very effective on learning holistic image and video r…
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Hwanjun Song, Deqing Sun, Sanghyuk Chun +5
Transformers are transforming the landscape of computer vision, especially for recognition tasks. Detection transformers are the first fully end-to-end learning systems for object…
Learning Continuous Environment Fields via Implicit Functions
Xueting Li, Shalini De Mello, Xiaolong Wang +3
We propose a novel scene representation that encodes reaching distance -- the distance between any position in the scene to a goal along a feasible trajectory. We demonstrate that…
Correcting Face Distortion in Wide-Angle Videos
Wei-Sheng Lai, YiChang Shih, Chia-Kai Liang +1
Video blogs and selfies are popular social media formats, which are often captured by wide-angle cameras to show human subjects and expanded background. Unfortunately, due to persp…
Learning Discriminative Shrinkage Deep Networks for Image Deconvolution
Pin-Hung Kuo, Jinshan Pan, Shao-Yi Chien +1
Most existing methods usually formulate the non-blind deconvolution problem into a maximum-a-posteriori framework and address it by manually designing kinds of regularization terms…
Video Frame Interpolation Transformer
Zhihao Shi, Xiangyu Xu, Xiaohong Liu +2
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights…
Hierarchical Modular Network for Video Captioning
Hanhua Ye, Guorong Li, Yuankai Qi +3
Video captioning aims to generate natural language descriptions according to the content, where representation learning plays a crucial role. Existing methods are mainly developed…
Restormer: Efficient Transformer for High-Resolution Image Restoration
Syed Waqas Zamir, Aditya Arora, Salman Khan +3
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoratio…