Search Results for author: James J. Little

Found 24 papers, 13 papers with code

Implicit and Explicit Commonsense for Multi-sentence Video Captioning

no code implementations14 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].

Imitation Learning Sentence +1

Semantically Enhanced Global Reasoning for Semantic Segmentation

no code implementations6 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.

Instance Segmentation Segmentation +1

UNeRF: Time and Memory Conscious U-Shaped Network for Training Neural Radiance Fields

no code implementations23 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.

Density Estimation Novel View Synthesis

OptiBox: Breaking the Limits of Proposals for Visual Grounding

no code implementations29 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).

Image Captioning Visual Grounding +1

Pan-tilt-zoom SLAM for Sports Videos

1 code implementation20 Jul 2019 Jikai Lu, Jianhui Chen, James J. Little

Rays overcome the missing depth in pure-rotation cameras.

Pose Estimation

Sports Camera Calibration via Synthetic Data

3 code implementations25 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.

Camera Calibration Generative Adversarial Network +1

A Less Biased Evaluation of Out-of-distribution Sample Detectors

3 code implementations13 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.

Image Classification

Learning Sports Camera Selection from Internet Videos

no code implementations8 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.

LSQ++: Lower running time and higher recall in multi-codebook quantization

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.

Quantization

A Two-point Method for PTZ Camera Calibration in Sports

1 code implementation26 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.

Camera Calibration Vocal Bursts Valence Prediction

Exploiting Points and Lines in Regression Forests for RGB-D Camera Relocalization

no code implementations28 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.

Camera Relocalization Loop Closure Detection +1

Backtracking Regression Forests for Accurate Camera Relocalization

1 code implementation22 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.

Camera Relocalization Loop Closure Detection +2

A simple yet effective baseline for 3d human pose estimation

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.

3D Pose Estimation Monocular 3D Human Pose Estimation

Play and Learn: Using Video Games to Train Computer Vision Models

no code implementations5 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.

Depth Estimation Domain Adaptation +3

Learning Online Smooth Predictors for Realtime Camera Planning Using Recurrent Decision Trees

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).

Real-Time Human Motion Capture with Multiple Depth Cameras

no code implementations25 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.

3D Pose Estimation Image Segmentation +2

Stacked Quantizers for Compositional Vector Compression

2 code implementations8 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.

Quantization

3D Pose from Motion for Cross-view Action Recognition via Non-linear Circulant Temporal Encoding

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.

Action Recognition Temporal Action Localization

Self-Learning for Player Localization in Sports Video

no code implementations27 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.

Self-Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.