1 code implementation • 10 Jan 2024 • Sicong Huang, JiaWei He, Kry Yik Chau Lui
Second, introducing new theoretic tools such as nearly essential support, essential distance and co-Lipschitzness, we obtain non-asymptotic provable OOD detection guarantees for certain distillation of the minimal sufficient statistics.
1 code implementation • 29 Nov 2023 • Yuqi Wang, JiaWei He, Lue Fan, Hongxin Li, Yuntao Chen, Zhaoxiang Zhang
In autonomous driving, predicting future events in advance and evaluating the foreseeable risks empowers autonomous vehicles to better plan their actions, enhancing safety and efficiency on the road.
no code implementations • 3 Oct 2023 • Qi Yan, Raihan Seraj, JiaWei He, Lili Meng, Tristan Sylvain
Following this, the chosen articles are subjected to zero-shot summarization to attain succinct context.
1 code implementation • 18 Sep 2023 • Ting Meng, Chunyun Fu, Mingguang Huang, Xiyang Wang, JiaWei He, Tao Huang, Wankai Shi
However, in terms of the detection confidence fusing classification and localization, objects of low detection confidence may have inaccurate localization but clear appearance; similarly, objects of high detection confidence may have inaccurate localization or unclear appearance; yet these objects are not further classified.
no code implementations • 8 Jun 2023 • JiaWei He, Lue Fan, Yuqi Wang, Yuntao Chen, Zehao Huang, Naiyan Wang, Zhaoxiang Zhang
In this paper, we rethink the data association in 2D MOT and utilize the 3D object representation to separate each object in the feature space.
no code implementations • 8 Jun 2023 • JiaWei He, Yuqi Wang, Yuntao Chen, Zhaoxiang Zhang
We devise the DoubleClustering algorithm to obtain object clusters from reconstructed scene-level points, and further enhance the model's detection capabilities by developing three stages of generalization: progressing from complete to partial, static to dynamic, and close to distant.
1 code implementation • 18 Apr 2023 • Xiyang Wang, Chunyun Fu, JiaWei He, Mingguang Huang, Ting Meng, Siyu Zhang, Hangning Zhou, Ziyao Xu, Chi Zhang
In the classical tracking-by-detection (TBD) paradigm, detection and tracking are separately and sequentially conducted, and data association must be properly performed to achieve satisfactory tracking performance.
1 code implementation • CVPR 2023 • JiaWei He, Yuntao Chen, Naiyan Wang, Zhaoxiang Zhang
We explore long-term temporal visual correspondence-based optimization for 3D video object detection in this work.
1 code implementation • 27 Mar 2023 • JiaWei He, Zehao Huang, Naiyan Wang, Zhaoxiang Zhang
Data association is at the core of many computer vision tasks, e. g., multiple object tracking, image matching, and point cloud registration.
1 code implementation • 3 Mar 2023 • JiaWei He, Chunyun Fu, Xiyang Wang
In the existing literature, most 3D multi-object tracking algorithms based on the tracking-by-detection framework employed deterministic tracks and detections for similarity calculation in the data association stage.
1 code implementation • 20 Jul 2022 • Yingyan Li, Yuntao Chen, JiaWei He, Zhaoxiang Zhang
So these methods only use a small number of projection constraints and produce insufficient depth candidates, leading to inaccurate depth estimation.
1 code implementation • 24 Feb 2022 • Xiyang Wang, Chunyun Fu, Zhankun Li, Ying Lai, JiaWei He
This association mechanism realizes tracking of an object in a 2D domain when the object is far away and only detected by the camera, and updating of the 2D trajectory with 3D information obtained when the object appears in the LiDAR field of view to achieve a smooth fusion of 2D and 3D trajectories.
Ranked #1 on Multi-Object Tracking on KITTI Tracking test
no code implementations • ICML Workshop INNF 2021 • Alexander Radovic, JiaWei He, Janahan Ramanan, Marcus A Brubaker, Andreas Lehrmann
In this work we describe OMEN, a neural ODE based normalizing flow for the prediction of marginal distributions at flexible evaluation horizons, and apply it to agent position forecasting.
no code implementations • ECCV 2020 • Mengyao Zhai, Lei Chen, JiaWei He, Megha Nawhal, Frederick Tung, Greg Mori
In contrast, we propose a parameter efficient framework, Piggyback GAN, which learns the current task by building a set of convolutional and deconvolutional filters that are factorized into filters of the models trained on previous tasks.
1 code implementation • CVPR 2021 • JiaWei He, Zehao Huang, Naiyan Wang, Zhaoxiang Zhang
Then the association problem turns into a general graph matching between tracklet graph and detection graph.
no code implementations • 25 Feb 2021 • Yu Gong, Hossein Hajimirsadeghi, JiaWei He, Thibaut Durand, Greg Mori
Learning from heterogeneous data poses challenges such as combining data from various sources and of different types.
no code implementations • 12 Feb 2021 • Huadong Liao, JiaWei He
In this paper, we show that the Jacobian determinant mapping is unique for the given distributions, hence the likelihood objective of flows has a unique global optimum.
no code implementations • 7 Oct 2020 • Joseph Marino, Lei Chen, JiaWei He, Stephan Mandt
We propose an approach for improving sequence modeling based on autoregressive normalizing flows.
no code implementations • 27 Mar 2020 • Huiqiang Zhong, Cunxiang Yin, Xiaohui Wu, Jinchang Luo, JiaWei He
The model consists of two modules: a station selector and an air quality regressor.
no code implementations • 18 Oct 2019 • Nazanin Mehrasa, Ruizhi Deng, Mohamed Osama Ahmed, Bo Chang, JiaWei He, Thibaut Durand, Marcus Brubaker, Greg Mori
Event sequences can be modeled by temporal point processes (TPPs) to capture their asynchronous and probabilistic nature.
no code implementations • pproximateinference AABI Symposium 2019 • Micael Carvalho, Thibaut Durand, JiaWei He, Nazanin Mehrasa, Greg Mori
In this paper, we propose an arbitrarily-conditioned data imputation framework built upon variational autoencoders and normalizing flows.
no code implementations • pproximateinference AABI Symposium 2019 • Yu Gong, Hossein Hajimirsadeghi, JiaWei He, Megha Nawhal, Thibaut Durand, Greg Mori
Despite promising progress on unimodal data imputation (e. g. image inpainting), models for multimodal data imputation are far from satisfactory.
no code implementations • 25 Sep 2019 • Yu Gong, Hossein Hajimirsadeghi, JiaWei He, Megha Nawhal, Thibaut Durand, Greg Mori
Learning from only partially-observed data for imputation has been an active research area.
2 code implementations • ICCV 2019 • Akash Abdu Jyothi, Thibaut Durand, JiaWei He, Leonid Sigal, Greg Mori
Recently there is an increasing interest in scene generation within the research community.
no code implementations • ICCV 2019 • Mengyao Zhai, Lei Chen, Fred Tung, JiaWei He, Megha Nawhal, Greg Mori
This makes it possible to perform image-conditioned generation tasks in a lifelong learning setting.
1 code implementation • 8 May 2019 • Huadong Liao, JiaWei He, Kunxian Shu
However, flow-based models are limited by density estimation performance issues as compared to state-of-the-art autoregressive models.
no code implementations • ICLR 2019 • Jiawei He, Yu Gong, Joseph Marino, Greg Mori, Andreas Lehrmann
In particular, we express the latent variable space of a variational autoencoder (VAE) in terms of a Bayesian network with a learned, flexible dependency structure.
no code implementations • CVPR 2019 • Nazanin Mehrasa, Akash Abdu Jyothi, Thibaut Durand, JiaWei He, Leonid Sigal, Greg Mori
We propose a novel probabilistic generative model for action sequences.
no code implementations • 10 Oct 2018 • Congqing He, Li Peng, Yuquan Le, JiaWei He, Xiangyu Zhu
In this paper, we propose a Sequence Enhanced Capsule model, dubbed as SECaps model, to relieve this problem.
1 code implementation • ECCV 2018 • Jiawei He, Andreas Lehrmann, Joseph Marino, Greg Mori, Leonid Sigal
Videos express highly structured spatio-temporal patterns of visual data.
no code implementations • 30 May 2017 • Jiawei He, Mostafa S. Ibrahim, Zhiwei Deng, Greg Mori
Our class-independent TPN outperforms other tubelet generation methods, and our unified temporal deep network achieves state-of-the-art localization results on all three datasets.