162 citations · 676 across the 18 of their papers we have counts for
19 papers
Does Visual Pretraining Help End-to-End Reasoning?
Chen Sun, Calvin Luo, Xingyi Zhou +2
We aim to investigate whether end-to-end learning of visual reasoning can be achieved with general-purpose neural networks, with the help of visual pretraining. A positive result w…
How can objects help action recognition?
Xingyi Zhou, Anurag Arnab, Chen Sun +1
Current state-of-the-art video models process a video clip as a long sequence of spatio-temporal tokens. However, they do not explicitly model objects, their interactions across th…
DaTaSeg: Taming a Universal Multi-Dataset Multi-Task Segmentation Model
Xiuye Gu, Yin Cui, Jonathan Huang +8
Observing the close relationship among panoptic, semantic and instance segmentation tasks, we propose to train a universal multi-dataset multi-task segmentation model: DaTaSeg.We u…
Dense Video Object Captioning from Disjoint Supervision
Xingyi Zhou, Anurag Arnab, Chen Sun +1
We propose a new task and model for dense video object captioning -- detecting, tracking and captioning trajectories of objects in a video. This task unifies spatial and temporal l…
NMS Strikes Back
Jeffrey Ouyang-Zhang, Jang Hyun Cho, Xingyi Zhou +1
Detection Transformer (DETR) directly transforms queries to unique objects by using one-to-one bipartite matching during training and enables end-to-end object detection. Recently,…
Global Tracking Transformers
Xingyi Zhou, Tianwei Yin, Vladlen Koltun +1
We present a novel transformer-based architecture for global multi-object tracking. Our network takes a short sequence of frames as input and produces global trajectories for all o…
Detecting Twenty-thousand Classes using Image-level Supervision
Xingyi Zhou, Rohit Girdhar, Armand Joulin +2
Current object detectors are limited in vocabulary size due to the small scale of detection datasets. Image classifiers, on the other hand, reason about much larger vocabularies, a…
Multimodal Virtual Point 3D Detection
Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl
Lidar-based sensing drives current autonomous vehicles. Despite rapid progress, current Lidar sensors still lag two decades behind traditional color cameras in terms of resolution…
Probabilistic two-stage detection
Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl
We develop a probabilistic interpretation of two-stage object detection. We show that this probabilistic interpretation motivates a number of common empirical training practices. I…
Simple multi-dataset detection
Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl
How do we build a general and broad object detection system? We use all labels of all concepts ever annotated. These labels span diverse datasets with potentially inconsistent taxo…
Center-based 3D Object Detection and Tracking
Tianwei Yin, Xingyi Zhou, Philipp Krähenbühl
Three-dimensional objects are commonly represented as 3D boxes in a point-cloud. This representation mimics the well-studied image-based 2D bounding-box detection but comes with ad…
Tracking Objects as Points
Xingyi Zhou, Vladlen Koltun, Philipp Krähenbühl
Tracking has traditionally been the art of following interest points through space and time. This changed with the rise of powerful deep networks. Nowadays, tracking is dominated b…
Objects as Points
Xingyi Zhou, Dequan Wang, Philipp Krähenbühl
Detection identifies objects as axis-aligned boxes in an image. Most successful object detectors enumerate a nearly exhaustive list of potential object locations and classify each.…
Bottom-up Object Detection by Grouping Extreme and Center Points
Xingyi Zhou, Jiacheng Zhuo, Philipp Krähenbühl
With the advent of deep learning, object detection drifted from a bottom-up to a top-down recognition problem. State of the art algorithms enumerate a near-exhaustive list of objec…
StarMap for Category-Agnostic Keypoint and Viewpoint Estimation
Xingyi Zhou, Arjun Karpur, Linjie Luo +1
Semantic keypoints provide concise abstractions for a variety of visual understanding tasks. Existing methods define semantic keypoints separately for each category with a fixed nu…
Unsupervised Domain Adaptation for 3D Keypoint Estimation via View Consistency
Xingyi Zhou, Arjun Karpur, Chuang Gan +2
In this paper, we introduce a novel unsupervised domain adaptation technique for the task of 3D keypoint prediction from a single depth scan or image. Our key idea is to utilize th…
Towards 3D Human Pose Estimation in the Wild: a Weakly-supervised Approach
Xingyi Zhou, Qixing Huang, Xiao Sun +2
In this paper, we study the task of 3D human pose estimation in the wild. This task is challenging due to lack of training data, as existing datasets are either in the wild images…
Deep Kinematic Pose Regression
Xingyi Zhou, Xiao Sun, Wei Zhang +2
Learning articulated object pose is inherently difficult because the pose is high dimensional but has many structural constraints. Most existing work do not model such constraints…
Model-based Deep Hand Pose Estimation
Xingyi Zhou, Qingfu Wan, Wei Zhang +2
Previous learning based hand pose estimation methods does not fully exploit the prior information in hand model geometry. Instead, they usually rely a separate model fitting step t…