27 citations · 75 across the 17 of their papers we have counts for
19 papers
World-T3: Test-Time Training as Persistent Memory for Real-Time Video World Models
Junyi Wu, Zekun Li, Chenhongyi Yang +9
Recent advances in video world models have enabled plausible interactive environments, yet long-horizon generation places a fundamental demand on visual memory: the previously obse…
Omni-Diffusion-Distill: Few-Step Distillation of Unified Multimodal Diffusion Large Language Models
Hong Huang, Chenhongyi Yang, Junzhe Sun +3
Unified multimodal diffusion large language models (dLLMs) offer a single architecture for both image generation and multimodal understanding, but their iterative decoding requires…
IMAGIN-4D: Image-Guided Controllable Interaction Generation
Sai Kumar Dwivedi, Federica Bogo, Buğra Tekin +6
Generating human-object interactions (HOI) is central to character animation, robotics, AR/VR, and embodied AI. Recent HOI generation methods synthesize motion from text, object ge…
EgoPoseFormer v2: Accurate Egocentric Human Motion Estimation for AR/VR
Zhenyu Li, Sai Kumar Dwivedi, Filip Maric +11
Egocentric human motion estimation is essential for AR/VR experiences, yet remains challenging due to limited body coverage from the egocentric viewpoint, frequent occlusions, and…
No time to train! Training-Free Reference-Based Instance Segmentation
Miguel Espinosa, Chenhongyi Yang, Linus Ericsson +2
The performance of image segmentation models has historically been constrained by the high cost of collecting large-scale annotated data. The Segment Anything Model (SAM) alleviate…
There is no SAMantics! Exploring SAM as a Backbone for Visual Understanding Tasks
Miguel Espinosa, Chenhongyi Yang, Linus Ericsson +2
The Segment Anything Model (SAM) was originally designed for label-agnostic mask generation. Does this model also possess inherent semantic understanding, of value to broader visua…
einspace: Searching for Neural Architectures from Fundamental Operations
Linus Ericsson, Miguel Espinosa, Chenhongyi Yang +5
Neural architecture search (NAS) finds high performing networks for a given task. Yet the results of NAS are fairly prosaic; they did not e.g. create a shift from convolutional str…
EgoPoseFormer: A Simple Baseline for Stereo Egocentric 3D Human Pose Estimation
Chenhongyi Yang, Anastasia Tkach, Shreyas Hampali +3
We present EgoPoseFormer, a simple yet effective transformer-based model for stereo egocentric human pose estimation. The main challenge in egocentric pose estimation is overcoming…
PlainMamba: Improving Non-Hierarchical Mamba in Visual Recognition
Chenhongyi Yang, Zehui Chen, Miguel Espinosa +4
We present PlainMamba: a simple non-hierarchical state space model (SSM) designed for general visual recognition. The recent Mamba model has shown how SSMs can be highly competitiv…
WidthFormer: Toward Efficient Transformer-based BEV View Transformation
Chenhongyi Yang, Tianwei Lin, Lichao Huang +1
We present WidthFormer, a novel transformer-based module to compute Bird's-Eye-View (BEV) representations from multi-view cameras for real-time autonomous-driving applications. Wid…
GPViT: A High Resolution Non-Hierarchical Vision Transformer with Group Propagation
Chenhongyi Yang, Jiarui Xu, Shalini De Mello +2
We present the Group Propagation Vision Transformer (GPViT): a novel nonhierarchical (i.e. non-pyramidal) transformer model designed for general visual recognition with high-resolu…
Plug and Play Active Learning for Object Detection
Chenhongyi Yang, Lichao Huang, Elliot J. Crowley
Annotating datasets for object detection is an expensive and time-consuming endeavor. To minimize this burden, active learning (AL) techniques are employed to select the most infor…
DETRDistill: A Universal Knowledge Distillation Framework for DETR-families
Jiahao Chang, Shuo Wang, Haiming Xu +3
Transformer-based detectors (DETRs) are becoming popular for their simple framework, but the large model size and heavy time consumption hinder their deployment in the real world.…
Prediction-Guided Distillation for Dense Object Detection
Chenhongyi Yang, Mateusz Ochal, Amos Storkey +1
Real-world object detection models should be cheap and accurate. Knowledge distillation (KD) can boost the accuracy of a small, cheap detection model by leveraging useful informati…
Contrastive Object-level Pre-training with Spatial Noise Curriculum Learning
Chenhongyi Yang, Lichao Huang, Elliot J. Crowley
The goal of contrastive learning based pre-training is to leverage large quantities of unlabeled data to produce a model that can be readily adapted downstream. Current approaches…
Disentangle Your Dense Object Detector
Zehui Chen, Chenhongyi Yang, Qiaofei Li +3
Deep learning-based dense object detectors have achieved great success in the past few years and have been applied to numerous multimedia applications such as video understanding.…
QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection
Chenhongyi Yang, Zehao Huang, Naiyan Wang
While general object detection with deep learning has achieved great success in the past few years, the performance and efficiency of detecting small objects are far from satisfact…
Consistency Regularization with High-dimensional Non-adversarial Source-guided Perturbation for Unsupervised Domain Adaptation in Segmentation
Kaihong Wang, Chenhongyi Yang, Margrit Betke
Unsupervised domain adaptation for semantic segmentation has been intensively studied due to the low cost of the pixel-level annotation for synthetic data. The most common approach…
Learning to Separate: Detecting Heavily-Occluded Objects in Urban Scenes
Chenhongyi Yang, Vitaly Ablavsky, Kaihong Wang +2
While visual object detection with deep learning has received much attention in the past decade, cases when heavy intra-class occlusions occur have not been studied thoroughly. In…