no code implementations • 15 Feb 2025 • Qiuxia Lin, Rongyu Chen, Kerui Gu, Angela Yao
To this end, we pioneer the integration of a semantics-aware motion prior for the test-time adaptation of 3D pose estimation.
1 code implementation • 13 Feb 2025 • Shihao Zhang, Yuguang Yan, Angela Yao
For deep regression, preserving the ordinality of the targets with respect to the feature representation improves performance across various tasks.
1 code implementation • 11 Feb 2025 • Sheng Zhou, Junbin Xiao, Qingyun Li, Yicong Li, Xun Yang, Dan Guo, Meng Wang, Tat-Seng Chua, Angela Yao
We introduce EgoTextVQA, a novel and rigorously constructed benchmark for egocentric QA assistance involving scene text.
no code implementations • 27 Dec 2024 • Kai Xu, Tze Ho Elden Tse, Jizong Peng, Angela Yao
Our proposed method is termed DAS3R, an abbreviation for Dynamics-Aware Gaussian Splatting for Static Scene Reconstruction.
no code implementations • 5 Dec 2024 • Bo Ji, Angela Yao
For this problem setting, we propose a context-based local super-resolution (CLSR) to super-resolve only specified regions of interest (ROI) while leveraging the entire image as context.
1 code implementation • 2 Dec 2024 • Bo Ji, Angela Yao
We propose a novel SfM-Free 3DGS (SFGS) method for video input, eliminating the need for known camera poses and SfM preprocessing.
1 code implementation • 2 Dec 2024 • Bo Ji, Angela Yao
State-of-the-art video deblurring methods use deep network architectures to recover sharpened video frames.
no code implementations • 25 Nov 2024 • Yuehan Zhang, Angela Yao
Self-supervised learning is crucial for super-resolution because ground-truth images are usually unavailable for real-world settings.
1 code implementation • 20 Nov 2024 • Minjoon Jung, Junbin Xiao, Byoung-Tak Zhang, Angela Yao
So we conduct a study on prediction consistency -- a key indicator for robustness and trustworthiness of temporal grounding.
1 code implementation • 2 Nov 2024 • Qing Zhong, Guodong Ding, Angela Yao
Temporal context plays a significant role in temporal action segmentation.
1 code implementation • 22 Sep 2024 • Sheng Zhou, Junbin Xiao, Xun Yang, Peipei Song, Dan Guo, Angela Yao, Meng Wang, Tat-Seng Chua
In this paper, we propose to study Grounded TextVideoQA by forcing models to answer questions and spatio-temporally localize the relevant scene-text regions, thus decoupling QA from scenetext recognition and promoting research towards interpretable QA.
no code implementations • 6 Sep 2024 • Hangyu Qin, Junbin Xiao, Angela Yao
In this paper, we present question-answering dense video events, a novel task that requires answering and grounding the dense-event questions in long videos, thus challenging MLLMs to faithfully comprehend and reason about multiple events occurring over extended time periods.
Ranked #1 on
Zero-Shot Video Question Answer
on NExT-GQA
1 code implementation • 19 Aug 2024 • Zhanzhong Pang, Fadime Sener, Shrinivas Ramasubramanian, Angela Yao
However, state-of-the-art temporal action segmentation methods overlook the long tail and fail to recognize tail actions.
1 code implementation • 8 Aug 2024 • Junbin Xiao, Nanxin Huang, Hangyu Qin, Dongyang Li, Yicong Li, Fengbin Zhu, Zhulin Tao, Jianxing Yu, Liang Lin, Tat-Seng Chua, Angela Yao
Video Large Language Models (Video-LLMs) are flourishing and has advanced many video-language tasks.
1 code implementation • 19 Jul 2024 • Yuehan Zhang, Angela Yao
However, channel attention leads to feature redundancy, as evidenced by the higher covariance among output channels.
no code implementations • 17 Jul 2024 • Zhongqun Zhang, Hengfei Wang, Ziwei Yu, Yihua Cheng, Angela Yao, Hyung Jin Chang
Given a language description of the hand and contact, NL2Contact generates realistic and faithful 3D hand-object contacts.
1 code implementation • 10 Jul 2024 • Yuehan Zhang, Seungjun Lee, Angela Yao
Standard single-image super-resolution creates paired training data from high-resolution images through fixed downsampling kernels.
no code implementations • 30 Jun 2024 • Fengyuan Yang, Kerui Gu, Ha Linh Nguyen, Tze Ho Elden Tse, Angela Yao
HAC benefits from geometric priors encoded in human mesh recovery models to estimate the SLAM scale and achieves precise global human motion estimation.
1 code implementation • CVPR 2024 • Fengyuan Yang, Kerui Gu, Angela Yao
To address these, we introduce Kinematic-Tree Rotation (KITRO), a novel mesh refinement strategy that explicitly models depth and human kinematic-tree structure.
1 code implementation • 22 Apr 2024 • Shihao Zhang, Kenji Kawaguchi, Angela Yao
Based on these two connections, we introduce PH-Reg, a regularizer specific to regression that matches the intrinsic dimension and topology of the feature space with the target space.
no code implementations • 5 Apr 2024 • Jiayin Zhu, Linlin Yang, Angela Yao
We present InstructHumans, a novel framework for instruction-driven 3D human texture editing.
1 code implementation • 26 Mar 2024 • Qiyuan He, Jinghao Wang, Ziwei Liu, Angela Yao
To that end, we introduce a novel training-free technique named Attention Interpolation via Diffusion (AID).
2 code implementations • 25 Mar 2024 • Zicong Fan, Takehiko Ohkawa, Linlin Yang, Nie Lin, Zhishan Zhou, Shihao Zhou, Jiajun Liang, Zhong Gao, Xuanyang Zhang, Xue Zhang, Fei Li, Zheng Liu, Feng Lu, Karim Abou Zeid, Bastian Leibe, Jeongwan On, Seungryul Baek, Aditya Prakash, Saurabh Gupta, Kun He, Yoichi Sato, Otmar Hilliges, Hyung Jin Chang, Angela Yao
A holistic 3Dunderstanding of such interactions from egocentric views is important for tasks in robotics, AR/VR, action recognition and motion generation.
1 code implementation • 14 Mar 2024 • Md Salman Shamil, Dibyadip Chatterjee, Fadime Sener, Shugao Ma, Angela Yao
3D hand pose is an underexplored modality for action recognition.
Ranked #1 on
Action Recognition
on H2O (2 Hands and Objects)
no code implementations • CVPR 2024 • Guodong Ding, Hans Golong, Angela Yao
Data replay is a successful incremental learning technique for images.
no code implementations • CVPR 2024 • Gianni Franchi, Olivier Laurent, Maxence Leguéry, Andrei Bursuc, Andrea Pilzer, Angela Yao
Deep Neural Networks (DNNs) are powerful tools for various computer vision tasks, yet they often struggle with reliable uncertainty quantification - a critical requirement for real-world applications.
no code implementations • 1 Dec 2023 • Kerui Gu, Zhihao LI, Shiyong Liu, Jianzhuang Liu, Songcen Xu, Youliang Yan, Michael Bi Mi, Kenji Kawaguchi, Angela Yao
Estimating 3D rotations is a common procedure for 3D computer vision.
Ranked #16 on
3D Human Pose Estimation
on 3DPW
no code implementations • 28 Nov 2023 • Kerui Gu, Rongyu Chen, Angela Yao
Most 2D human pose estimation frameworks estimate keypoint confidence in an ad-hoc manner, using heuristics such as the maximum value of heatmaps.
Ranked #1 on
Pose Estimation
on COCO val2017
no code implementations • CVPR 2024 • Haipeng Xiong, Angela Yao
To improve regression performance over the entire range of data, we propose to construct hierarchical classifiers for solving imbalanced regression tasks.
1 code implementation • 30 Sep 2023 • Kai Xu, Rongyu Chen, Gianni Franchi, Angela Yao
The capacity of a modern deep learning system to determine if a sample falls within its realm of knowledge is fundamental and important.
Ranked #1 on
Out-of-Distribution Detection
on Far-OOD
Out-of-Distribution Detection
Out of Distribution (OOD) Detection
no code implementations • 27 Sep 2023 • Xuanlong Yu, Yi Zuo, Zitao Wang, Xiaowen Zhang, Jiaxuan Zhao, Yuting Yang, Licheng Jiao, Rui Peng, Xinyi Wang, Junpei Zhang, Kexin Zhang, Fang Liu, Roberto Alcover-Couso, Juan C. SanMiguel, Marcos Escudero-Viñolo, Hanlin Tian, Kenta Matsui, Tianhao Wang, Fahmy Adan, Zhitong Gao, Xuming He, Quentin Bouniot, Hossein Moghaddam, Shyam Nandan Rai, Fabio Cermelli, Carlo Masone, Andrea Pilzer, Elisa Ricci, Andrei Bursuc, Arno Solin, Martin Trapp, Rui Li, Angela Yao, Wenlong Chen, Ivor Simpson, Neill D. F. Campbell, Gianni Franchi
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023.
1 code implementation • CVPR 2024 • Junbin Xiao, Angela Yao, Yicong Li, Tat Seng Chua
We study visually grounded VideoQA in response to the emerging trends of utilizing pretraining techniques for video-language understanding.
1 code implementation • 25 Aug 2023 • Jiayin Zhu, Zhuoran Zhao, Linlin Yang, Angela Yao
We present HiFiHR, a high-fidelity hand reconstruction approach that utilizes render-and-compare in the learning-based framework from a single image, capable of generating visually plausible and accurate 3D hand meshes while recovering realistic textures.
1 code implementation • NeurIPS 2023 • Dibyadip Chatterjee, Fadime Sener, Shugao Ma, Angela Yao
Given a set of verbs and objects observed during training, the goal is to generalize the verbs to an open vocabulary of actions with seen and novel objects.
Ranked #1 on
Open Vocabulary Action Recognition
on Assembly101
(using extra training data)
no code implementations • 1 Aug 2023 • Marwane Hariat, Olivier Laurent, Rémi Kazmierczak, Shihao Zhang, Andrei Bursuc, Angela Yao, Gianni Franchi
We propose a novel approach to improve the robustness of semantic segmentation techniques by leveraging the synergy between label-to-image generators and image-to-label segmentation models.
no code implementations • 31 Jul 2023 • Guodong Ding, Fadime Sener, Shugao Ma, Angela Yao
Our framework constructs a knowledge base with spatial and temporal beliefs based on observed mistakes.
no code implementations • CVPR 2023 • Ziwei Yu, Chen Li, Linlin Yang, Xiaoxu Zheng, Michael Bi Mi, Gim Hee Lee, Angela Yao
However, the reconstructed meshes are prone to artifacts and do not appear as plausible hand shapes.
1 code implementation • CVPR 2024 • Kai Xu, Ziwei Yu, Xin Wang, Michael Bi Mi, Angela Yao
We show that bilinear interpolation inherently attenuates high-frequency information while an MLP-based coordinate network can approximate more frequencies.
Ranked #2 on
Video Super-Resolution
on REDS4- 4x upscaling
1 code implementation • 27 Feb 2023 • Junbin Xiao, Pan Zhou, Angela Yao, Yicong Li, Richang Hong, Shuicheng Yan, Tat-Seng Chua
CoVGT's uniqueness and superiority are three-fold: 1) It proposes a dynamic graph transformer module which encodes video by explicitly capturing the visual objects, their relations and dynamics, for complex spatio-temporal reasoning.
Ranked #22 on
Video Question Answering
on NExT-QA
(using extra training data)
no code implementations • 25 Jan 2023 • Kerui Gu, Linlin Yang, Michael Bi Mi, Angela Yao
Experimental results on both the human body and hand benchmarks show that BCIR is faster to train and more accurate than the original integral regression, making it competitive with state-of-the-art detection methods.
1 code implementation • 21 Jan 2023 • Shihao Zhang, Linlin Yang, Michael Bi Mi, Xiaoxu Zheng, Angela Yao
In computer vision, it is often observed that formulating regression problems as a classification task often yields better performance.
Ranked #19 on
Crowd Counting
on ShanghaiTech B
1 code implementation • ICCV 2023 • Rongyu Chen, Linlin Yang, Angela Yao
For monocular RGB-based 3D pose and shape estimation, multiple solutions are often feasible due to factors like occlusion and truncation.
Ranked #1 on
Multi-Hypotheses 3D Human Pose Estimation
on AH36M
no code implementations • CVPR 2023 • Qiyuan He, Linlin Yang, Kerui Gu, Qiuxia Lin, Angela Yao
We present Pose Integrated Gradient (PoseIG), the first interpretability technique designed for pose estimation.
no code implementations • CVPR 2023 • Qiuxia Lin, Linlin Yang, Angela Yao
To solve this problem, we present a framework for cross-domain semi-supervised hand pose estimation and target the challenging scenario of learning models from labelled multi-modal synthetic data and unlabelled real-world data.
no code implementations • 20 Dec 2022 • Dipika Singhania, Rahul Rahaman, Angela Yao
For the task of temporal action segmentation, we propose an encoder-decoder-style architecture named C2F-TCN featuring a "coarse-to-fine" ensemble of decoder outputs.
no code implementations • 24 Nov 2022 • Ziwei Yu, Linlin Yang, You Xie, Ping Chen, Angela Yao
We propose a novel framework for 3D hand shape reconstruction and hand-object grasp optimization from a single RGB image.
Ranked #5 on
3D Hand Pose Estimation
on HO-3D v3
3 code implementations • 19 Oct 2022 • Guodong Ding, Fadime Sener, Angela Yao
Temporal action segmentation (TAS) in videos aims at densely identifying video frames in minutes-long videos with multiple action classes.
1 code implementation • 5 Aug 2022 • Yuehan Zhang, Bo Ji, Jia Hao, Angela Yao
In image super-resolution, both pixel-wise accuracy and perceptual fidelity are desirable.
1 code implementation • 20 Jul 2022 • Haipeng Xiong, Angela Yao
Through a series of experiments on carefully controlled synthetic data, we show that this counter-intuitive result is caused by imprecise ground truth local counts.
no code implementations • 20 Jul 2022 • Rahul Rahaman, Dipika Singhania, Alexandre Thiery, Angela Yao
In temporal action segmentation, Timestamp supervision requires only a handful of labelled frames per video sequence.
no code implementations • 18 Jul 2022 • Guodong Ding, Angela Yao
To this end, we propose two novel loss functions for the unlabelled data: an action affinity loss and an action continuity loss.
no code implementations • 28 Apr 2022 • Shaohui Lin, Bo Ji, Rongrong Ji, Angela Yao
Multi-exit architectures consist of a backbone and branch classifiers that offer shortened inference pathways to reduce the run-time of deep neural networks.
no code implementations • CVPR 2022 • You Xie, Huiqi Mao, Angela Yao, Nils Thuerey
We propose a novel approach to generate temporally coherent UV coordinates for loose clothing.
1 code implementation • CVPR 2022 • Bo Ji, Angela Yao
Video deblurring has achieved remarkable progress thanks to the success of deep neural networks.
Ranked #3 on
Analog Video Restoration
on TAPE
1 code implementation • CVPR 2022 • Fadime Sener, Dibyadip Chatterjee, Daniel Shelepov, Kun He, Dipika Singhania, Robert Wang, Angela Yao
Assembly101 is a new procedural activity dataset featuring 4321 videos of people assembling and disassembling 101 "take-apart" toy vehicles.
1 code implementation • 28 Feb 2022 • Joya Chen, Kai Xu, Yuhui Wang, Yifei Cheng, Angela Yao
A standard hardware bottleneck when training deep neural networks is GPU memory.
1 code implementation • 13 Dec 2021 • Ziwei Yu, Linlin Yang, Shicheng Chen, Angela Yao
This paper addresses the 3D point cloud reconstruction and 3D pose estimation of the human hand from a single RGB image.
1 code implementation • 12 Dec 2021 • Junbin Xiao, Angela Yao, Zhiyuan Liu, Yicong Li, Wei Ji, Tat-Seng Chua
To align with the multi-granular essence of linguistic concepts in language queries, we propose to model video as a conditional graph hierarchy which weaves together visual facts of different granularity in a level-wise manner, with the guidance of corresponding textual cues.
Ranked #6 on
Video Question Answering
on IntentQA
1 code implementation • 2 Dec 2021 • Dipika Singhania, Rahul Rahaman, Angela Yao
Our method hinges on unsupervised representation learning, which, for temporal action segmentation, poses unique challenges.
1 code implementation • 15 Nov 2021 • Haotong Zhang, Fuhai Chen, Angela Yao
We present a (semi-) weakly supervised method using only a small number of fully-labelled sequences and predominantly sequences in which only the (one) upcoming action is labelled.
no code implementations • ICLR 2022 • Kerui Gu, Linlin Yang, Angela Yao
We do a deep dive on the inference and back-propagation of integral pose regression to better understand the causes behind the performance and training differences.
no code implementations • 15 Aug 2021 • Guodong Ding, Angela Yao
Due to the lack of action-level supervision, we adopt the Hungarian matching algorithm to relate latent action prototypes to ground truth semantic classes for evaluation.
2 code implementations • 2 Aug 2021 • Gianni Franchi, Nacim Belkhir, Mai Lan Ha, Yufei Hu, Andrei Bursuc, Volker Blanz, Angela Yao
Along with predictive performance and runtime speed, reliability is a key requirement for real-world semantic segmentation.
2 code implementations • CVPR 2022 • Kai Xu, Angela Yao
We propose an efficient plug-and-play acceleration framework for semi-supervised video object segmentation by exploiting the temporal redundancies in videos presented by the compressed bitstream.
1 code implementation • CVPR 2021 • Junbin Xiao, Xindi Shang, Angela Yao, Tat-Seng Chua
We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions.
1 code implementation • 14 Jun 2021 • Yufei Hu, Nacim Belkhir, Jesus Angulo, Angela Yao, Gianni Franchi
Using a combination of linear and non-linear procedures is critical for generating a sufficiently deep feature space.
1 code implementation • 6 Jun 2021 • Fadime Sener, Dibyadip Chatterjee, Angela Yao
At what temporal scale should they be derived?
Ranked #5 on
Action Anticipation
on EPIC-KITCHENS-100 (test)
no code implementations • 6 Jun 2021 • Fadime Sener, Rishabh Saraf, Angela Yao
Can we teach a robot to recognize and make predictions for activities that it has never seen before?
no code implementations • 6 Jun 2021 • Abhinav Rai, Fadime Sener, Angela Yao
Modeling the visual changes that an action brings to a scene is critical for video understanding.
9 code implementations • 25 May 2021 • Yanbo Wang, Shaohui Lin, Yanyun Qu, Haiyan Wu, Zhizhong Zhang, Yuan Xie, Angela Yao
Convolutional neural networks (CNNs) are highly successful for super-resolution (SR) but often require sophisticated architectures with heavy memory cost and computational overhead, significantly restricts their practical deployments on resource-limited devices.
1 code implementation • 23 May 2021 • Dipika Singhania, Rahul Rahaman, Angela Yao
In this work, we propose a novel temporal encoder-decoder to tackle the problem of sequence fragmentation.
Ranked #4 on
Action Segmentation
on Assembly101
2 code implementations • 18 May 2021 • Junbin Xiao, Xindi Shang, Angela Yao, Tat-Seng Chua
We introduce NExT-QA, a rigorously designed video question answering (VideoQA) benchmark to advance video understanding from describing to explaining the temporal actions.
no code implementations • Environmental Health 2021 • Jessica Yu, Kaitlin Castellani, Krista Forysinski, Paul Gustafson, James Lu, Emily Peterson, Martino Tran, Angela Yao, Jingxuan Zhao, and Michael Brauer
In addition to an overall vulnerability score, exposure, adaptive capacity, and sensitivity sub-scores were computed for each hazard.
no code implementations • ICCV 2021 • Linlin Yang, Shicheng Chen, Angela Yao
By design, we introduce data augmentation of differing difficulties, consistency regularizer, label correction and sample selection for RGB-based 3D hand pose estimation.
no code implementations • ICCV 2021 • Kerui Gu, Linlin Yang, Angela Yao
Heatmap-based detection methods are dominant for 2D human pose estimation even though regression is more intuitive.
Ranked #5 on
Pose Estimation
on COCO val2017
no code implementations • 19 Oct 2020 • Soumajit Majumder, Ansh Khurana, Abhinav Rai, Angela Yao
Segmenting objects of interest in an image is an essential building block of applications such as photo-editing and image analysis.
no code implementations • 18 Oct 2020 • Soumajit Majumder, Angela Yao
In current interactive instance segmentation works, the user is granted a free hand when providing clicks to segment an object; clicks are allowed on background pixels and other object instances far from the target object.
3 code implementations • 22 Jul 2020 • Kamalesh Palanisamy, Dipika Singhania, Angela Yao
Besides, we show that even though we use the pretrained model weights for initialization, there is variance in performance in various output runs of the same model.
Environmental Sound Classification
General Classification
+2
2 code implementations • ECCV 2020 • Fadime Sener, Dipika Singhania, Angela Yao
Future prediction, especially in long-range videos, requires reasoning from current and past observations.
Ranked #2 on
Action Anticipation
on Assembly101
1 code implementation • 20 Apr 2020 • Moritz Wolter, Shaohui Lin, Angela Yao
Linear layers still occupy a significant portion of the parameters in recurrent neural networks (RNNs).
1 code implementation • 28th European Symposium on Artificial Neural Networks, Computational Intelligence and Machine Learning 2020 • Moritz Wolter, Angela Yao, and Sven Behnke
The ability to anticipate the future is essential for ac-tion planning in autonomous systems.
no code implementations • ECCV 2020 • Anil Armagan, Guillermo Garcia-Hernando, Seungryul Baek, Shreyas Hampali, Mahdi Rad, Zhaohui Zhang, Shipeng Xie, Mingxiu Chen, Boshen Zhang, Fu Xiong, Yang Xiao, Zhiguo Cao, Junsong Yuan, Pengfei Ren, Weiting Huang, Haifeng Sun, Marek Hrúz, Jakub Kanis, Zdeněk Krňoul, Qingfu Wan, Shile Li, Linlin Yang, Dongheui Lee, Angela Yao, Weiguo Zhou, Sijia Mei, Yun-hui Liu, Adrian Spurr, Umar Iqbal, Pavlo Molchanov, Philippe Weinzaepfel, Romain Brégier, Grégory Rogez, Vincent Lepetit, Tae-Kyun Kim
To address these issues, we designed a public challenge (HANDS'19) to evaluate the abilities of current 3D hand pose estimators (HPEs) to interpolate and extrapolate the poses of a training set.
no code implementations • 13 Dec 2019 • Julian Tanke, Oh-Hun Kwon, Patrick Stotko, Radu Alexandru Rosu, Michael Weinmann, Hassan Errami, Sven Behnke, Maren Bennewitz, Reinhard Klein, Andreas Weber, Angela Yao, Juergen Gall
The key prerequisite for accessing the huge potential of current machine learning techniques is the availability of large databases that capture the complex relations of interest.
no code implementations • ECCV 2020 • Chengde Wan, Thomas Probst, Luc van Gool, Angela Yao
In the first stage, the network estimates a dense correspondence field for every pixel on the depth map or image grid to the mesh grid.
2 code implementations • 13 Dec 2018 • Moritz Wolter, Juergen Gall, Angela Yao
Fourier methods have a long and proven track record as an excellent tool in data processing.
no code implementations • 10 Dec 2018 • Gianni Franchi, Angela Yao, Andreas Kolb
We propose a novel single-image super-resolution approach based on the geostatistical method of kriging.
no code implementations • 9 Dec 2018 • Divyansh Aggarwal, Elchin Valiyev, Fadime Sener, Angela Yao
When judging style, a key question that often arises is whether or not a pair of objects are compatible with each other.
no code implementations • 7 Dec 2018 • Soumajit Majumder, Angela Yao
In interactive instance segmentation, users give feedback to iteratively refine segmentation masks.
no code implementations • ICCV 2019 • Fadime Sener, Angela Yao
How can we teach a robot to predict what will happen next for an activity it has never seen before?
no code implementations • CVPR 2019 • Linlin Yang, Angela Yao
Hand image synthesis and pose estimation from RGB images are both highly challenging tasks due to the large discrepancy between factors of variation ranging from image background content to camera viewpoint.
no code implementations • 25 Oct 2018 • Iason Oikonomidis, Guillermo Garcia-Hernando, Angela Yao, Antonis Argyros, Vincent Lepetit, Tae-Kyun Kim
The fourth instantiation of this workshop attracted significant interest from both academia and the industry.
1 code implementation • NeurIPS 2018 • Moritz Wolter, Angela Yao
Complex numbers have long been favoured for digital signal processing, yet complex representations rarely appear in deep learning architectures.
no code implementations • CVPR 2018 • Fadime Sener, Angela Yao
This paper presents a new method for unsupervised segmentation of complex activities from video into multiple steps, or sub-activities, without any textual input.
1 code implementation • CVPR 2018 • Chengde Wan, Thomas Probst, Luc van Gool, Angela Yao
Specifically, we decompose the pose parameters into a set of per-pixel estimations, i. e., 2D heat maps, 3D heat maps and unit 3D directional vector fields.
Ranked #4 on
Hand Pose Estimation
on MSRA Hands
no code implementations • CVPR 2017 • Chengde Wan, Thomas Probst, Luc van Gool, Angela Yao
Regressing the hand pose can then be done by learning a discriminator to estimate the posterior of the latent pose given some depth maps.
no code implementations • ICCV 2017 • Jun Li, Reinhard Klein, Angela Yao
Estimating depth from a single RGB image is an ill-posed and inherently ambiguous problem.
Ranked #75 on
Monocular Depth Estimation
on NYU-Depth V2
(RMSE metric)
no code implementations • 10 Apr 2016 • Chengde Wan, Angela Yao, Luc van Gool
We present a hierarchical regression framework for estimating hand joint positions from single depth images based on local surface normals.
no code implementations • 22 Oct 2015 • Björn Krüger, Anna Vögele, Tobias Willig, Angela Yao, Reinhard Klein, Andreas Weber
We introduce a method for automated temporal segmentation of human motion data into distinct actions and compositing motion primitives based on self-similar structures in the motion sequence.
no code implementations • CVPR 2014 • Angela Yao, Luc van Gool, Pushmeet Kohli
Human gestures, similar to speech and handwriting, are often unique to the individual.
no code implementations • NeurIPS 2011 • Angela Yao, Juergen Gall, Luc V. Gool, Raquel Urtasun
A common approach for handling the complexity and inherent ambiguities of 3D human pose estimation is to use pose priors learned from training data.