no code implementations • 14 Mar 2023 • Shih-Han Chou, James J. Little, Leonid Sigal
We show that our commonsense knowledge enhanced approach produces significant improvements on this task (up to 57% in METEOR and 8. 5% in CIDEr), as well as the state-of-the-art result on more traditional video captioning in the ActivityNet Captions dataset [29].
no code implementations • 6 Dec 2022 • Mir Rayat Imtiaz Hossain, Leonid Sigal, James J. Little
Recent advances in pixel-level tasks (e. g., segmentation) illustrate the benefit of long-range interactions between aggregated region-based representations that can enhance local features.
1 code implementation • 27 Oct 2022 • Aritro Roy Arko, James J. Little, Kwang Moo Yi
We propose a bootstrapping framework to enhance human optical flow and pose.
no code implementations • 23 Jun 2022 • Abiramy Kuganesan, Shih-Yang Su, James J. Little, Helge Rhodin
Neural Radiance Fields (NeRFs) increase reconstruction detail for novel view synthesis and scene reconstruction, with applications ranging from large static scenes to dynamic human motion.
1 code implementation • CVPR 2022 • Bastian Wandt, James J. Little, Helge Rhodin
Human pose estimation from single images is a challenging problem that is typically solved by supervised learning.
Ranked #1 on Unsupervised 3D Human Pose Estimation on Human3.6M
3D Human Pose Estimation Unsupervised 3D Human Pose Estimation +1
no code implementations • 29 Nov 2019 • Zicong Fan, Si Yi Meng, Leonid Sigal, James J. Little
The problem of language grounding has attracted much attention in recent years due to its pivotal role in more general image-lingual high level reasoning tasks (e. g., image captioning, VQA).
1 code implementation • 20 Jul 2019 • Jikai Lu, Jianhui Chen, James J. Little
Rays overcome the missing depth in pure-rotation cameras.
3 code implementations • 25 Oct 2018 • Jianhui Chen, James J. Little
Here we propose a highly automatic method for calibrating sports cameras from a single image using synthetic data.
3 code implementations • 13 Sep 2018 • Alireza Shafaei, Mark Schmidt, James J. Little
What makes this problem different from a typical supervised learning setting is that the distribution of outliers used in training may not be the same as the distribution of outliers encountered in the application.
no code implementations • 8 Sep 2018 • Jianhui Chen, Keyu Lu, Sijia Tian, James J. Little
This work addresses camera selection, the task of predicting which camera should be "on air" from multiple candidate cameras for soccer broadcast.
1 code implementation • ECCV 2018 • Julieta Martinez, Shobhit Zakhmi, Holger H. Hoos, James J. Little
Multi-codebook quantization (MCQ) is the task of expressing a set of vectors as accurately as possible in terms of discrete entries in multiple bases.
1 code implementation • ECCV 2018 • Mir Rayat Imtiaz Hossain, James J. Little
In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses.
Ranked #187 on 3D Human Pose Estimation on Human3.6M
1 code implementation • 26 Jan 2018 • Jianhui Chen, Fangrui Zhu, James J. Little
We also propose a fast random forest method to predict pan-tilt angles without image-to-image feature matching, leading to an efficient calibration method for new images.
1 code implementation • 23 Nov 2017 • Mir Rayat Imtiaz Hossain, James J. Little
In this work, we address the problem of 3D human pose estimation from a sequence of 2D human poses.
Ranked #12 on 3D Human Pose Estimation on HumanEva-I
no code implementations • 28 Oct 2017 • Lili Meng, Frederick Tung, James J. Little, Julien Valentin, Clarence de Silva
Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure and loop closure detection.
1 code implementation • 22 Oct 2017 • Lili Meng, Jianhui Chen, Frederick Tung, James J. Little, Julien Valentin, Clarence W. de Silva
Camera relocalization plays a vital role in many robotics and computer vision tasks, such as global localization, recovery from tracking failure, and loop closure detection.
no code implementations • 29 Sep 2017 • Keyu Lu, Jianhui Chen, James J. Little, Hangen He
Vision based player detection is important in sports applications.
14 code implementations • ICCV 2017 • Julieta Martinez, Rayat Hossain, Javier Romero, James J. Little
Following the success of deep convolutional networks, state-of-the-art methods for 3d human pose estimation have focused on deep end-to-end systems that predict 3d joint locations given raw image pixels.
Ranked #18 on 3D Human Pose Estimation on HumanEva-I
no code implementations • 5 Aug 2016 • Alireza Shafaei, James J. Little, Mark Schmidt
We present experiments assessing the effectiveness on real-world data of systems trained on synthetic RGB images that are extracted from a video game.
no code implementations • CVPR 2016 • Jianhui Chen, Hoang M. Le, Peter Carr, Yisong Yue, James J. Little
We study the problem of online prediction for realtime camera planning, where the goal is to predict smooth trajectories that correctly track and frame objects of interest (e. g., players in a basketball game).
no code implementations • 25 May 2016 • Alireza Shafaei, James J. Little
Commonly used human motion capture systems require intrusive attachment of markers that are visually tracked with multiple cameras.
2 code implementations • 8 Nov 2014 • Julieta Martinez, Holger H. Hoos, James J. Little
Recently, Babenko and Lempitsky introduced Additive Quantization (AQ), a generalization of Product Quantization (PQ) where a non-independent set of codebooks is used to compress vectors into small binary codes.
1 code implementation • CVPR 2014 • Ankur Gupta, Julieta Martinez, James J. Little, Robert J. Woodham
We describe a new approach to transfer knowledge across views for action recognition by using examples from a large collection of unlabelled mocap data.
no code implementations • 27 Jul 2013 • Kenji Okuma, David G. Lowe, James J. Little
This paper introduces a novel self-learning framework that automates the label acquisition process for improving models for detecting players in broadcast footage of sports games.