b'Simon See'

research

∙ 09/15/2023

Self-Consistent Narrative Prompts on Abductive Natural Language Inference

Abduction has long been seen as crucial for narrative comprehension and ...

0 Chunkit Chan, et al. ∙

research

∙ 08/10/2023

Learning Gabor Texture Features for Fine-Grained Recognition

Extracting and using class-discriminative features is critical for fine-...

0 Lanyun Zhu, et al. ∙

research

∙ 07/31/2023

Towards Building AI-CPS with NVIDIA Isaac Sim: An Industrial Benchmark and Case Study for Robotics Manipulation

As a representative cyber-physical system (CPS), robotic manipulator has...

0 Zhehua Zhou, et al. ∙

research

∙ 06/14/2023

Towards Balanced Active Learning for Multimodal Classification

Training multimodal networks requires a vast amount of data due to their...

0 Meng Shen, et al. ∙

research

∙ 06/09/2023

TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses

3D multi-object tracking (MOT) is vital for many applications including ...

0 Xuesong Chen, et al. ∙

research

∙ 06/04/2023

A Unified Framework for Factorizing Distributional Value Functions for Multi-Agent Reinforcement Learning

In fully cooperative multi-agent reinforcement learning (MARL) settings,...

0 Wei-Fang Sun, et al. ∙

research

∙ 05/06/2023

Wasserstein-Fisher-Rao Embedding: Logical Query Embeddings with Local Comparison and Global Transport

Answering complex queries on knowledge graphs is important but particula...

0 Zihao Wang, et al. ∙

research

∙ 04/11/2023

Continual Semantic Segmentation with Automatic Memory Sample Selection

Continual Semantic Segmentation (CSS) extends static semantic segmentati...

0 Lanyun Zhu, et al. ∙

research

∙ 03/15/2023

VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation

We introduce VideoFlow, a novel optical flow estimation framework for vi...

0 Xiaoyu Shi, et al. ∙

research

∙ 03/02/2023

FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation

FlowFormer introduces a transformer architecture into optical flow estim...

0 Xiaoyu Shi, et al. ∙

research

∙ 01/21/2023

Logical Message Passing Networks with One-hop Inference on Atomic Formulas

Complex Query Answering (CQA) over Knowledge Graphs (KGs) has attracted ...

0 Zihao Wang, et al. ∙

research

∙ 01/01/2023

MIGPerf: A Comprehensive Benchmark for Deep Learning Training and Inference Workloads on Multi-Instance GPUs

New architecture GPUs like A100 are now equipped with multi-instance GPU...

0 Huaizheng Zhang, et al. ∙

research

∙ 12/17/2022

Inductive Attention for Video Action Anticipation

Anticipating future actions based on video observations is an important ...

8 Tsung-Ming Tai, et al. ∙

research

∙ 11/23/2022

NAS-LID: Efficient Neural Architecture Search with Local Intrinsic Dimension

One-shot neural architecture search (NAS) substantially improves the sea...

0 Xin He, et al. ∙

research

∙ 11/07/2022

Complex Hyperbolic Knowledge Graph Embeddings with Fast Fourier Transform

The choice of geometric space for knowledge graph (KG) embeddings can ha...

0 Huiru Xiao, et al. ∙

research

∙ 11/02/2022

CAMANet: Class Activation Map Guided Attention Network for Radiology Report Generation

Radiology report generation (RRG) has gained increasing research attenti...

0 Jun Wang, et al. ∙

research

∙ 10/14/2022

PseudoReasoner: Leveraging Pseudo Labels for Commonsense Knowledge Base Population

Commonsense Knowledge Base (CSKB) Population aims at reasoning over unse...

0 Tianqing Fang, et al. ∙

research

∙ 10/13/2022

SubeventWriter: Iterative Sub-event Sequence Generation with Coherence Controller

In this paper, we propose a new task of sub-event generation for an unse...

0 Zhaowei Wang, et al. ∙

research

∙ 10/02/2022

Saving the Limping: Fault-tolerant Quadruped Locomotion via Reinforcement Learning

Quadruped locomotion now has acquired the skill to traverse or even spri...

0 Dikai Liu, et al. ∙

research

∙ 07/04/2022

Attributed Abnormality Graph Embedding for Clinically Accurate X-Ray Report Generation

Automatic generation of medical reports from X-ray images can assist rad...

0 Sixing Yan, et al. ∙

research

∙ 06/22/2022

NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022

In this report, we describe the technical details of our submission for ...

11 Tsung-Ming Tai, et al. ∙

research

∙ 06/02/2022

Unified Recurrence Modeling for Video Action Anticipation

Forecasting future events based on evidence of current conditions is an ...

9 Tsung-Ming Tai, et al. ∙

research

∙ 10/18/2021

Speech Representation Learning Through Self-supervised Pretraining And Multi-task Finetuning

Speech representation learning plays a vital role in speech processing. ...

0 Yi-Chen Chen, et al. ∙

research

∙ 09/26/2021

Self-Supervised Video Representation Learning by Video Incoherence Detection

This paper introduces a novel self-supervised method that leverages inco...

0 Haozhi Cao, et al. ∙

research

∙ 07/11/2021

Aligning Correlation Information for Domain Adaptation in Action Recognition

Domain adaptation (DA) approaches address domain shift and enable networ...

0 Yuecong Xu, et al. ∙

research

∙ 08/26/2020

Effective Action Recognition with Embedded Key Point Shifts

Temporal feature extraction is an essential technique in video-based act...

0 Haozhi Cao, et al. ∙

research

∙ 07/07/2020

A deep learning based nonlinear upscaling method for transport equations

We will develop a nonlinear upscaling method for nonlinear transport equ...

0 Tak Shing Au Yeung, et al. ∙

research

∙ 06/09/2020

PNL: Efficient Long-Range Dependencies Extraction with Pyramid Non-Local Module for Action Recognition

Long-range spatiotemporal dependencies capturing plays an essential role...

0 Yuecong Xu, et al. ∙

research

∙ 06/06/2020

ARID: A New Dataset for Recognizing Action in the Dark

The task of action recognition in dark videos is useful in various scena...

0 Yuecong Xu, et al. ∙

research

∙ 05/06/2020

Exploiting Inter-Frame Regional Correlation for Efficient Action Recognition

Temporal feature extraction is an important issue in video-based action ...

9 Yuecong Xu, et al. ∙

research

∙ 03/08/2020

Dependently Typed Knowledge Graphs

Reasoning over knowledge graphs is traditionally built upon a hierarchy ...

0 Zhangsheng Lai, et al. ∙

research

∙ 11/20/2019

Understanding Top-k Sparsification in Distributed Deep Learning

Distributed stochastic gradient descent (SGD) algorithms are widely depl...

0 Shaohuai Shi, et al. ∙

research

∙ 07/09/2019

Improving Deep Lesion Detection Using 3D Contextual and Spatial Attention

Lesion detection from computed tomography (CT) scans is challenging comp...

3 Qingyi Tao, et al. ∙

research

∙ 10/10/2018

Secure Deep Learning Engineering: A Software Quality Assurance Perspective

Over the past decades, deep learning (DL) systems have achieved tremendo...

0 Lei Ma, et al. ∙

research

∙ 09/04/2018

DeepHunter: Hunting Deep Neural Network Defects via Coverage-Guided Fuzzing

In company with the data explosion over the past decade, deep neural net...

0 Xiaofei Xie, et al. ∙

research

∙ 09/04/2018

Coverage-Guided Fuzzing for Deep Neural Networks

In company with the data explosion over the past decade, deep neural net...

0 Xiaofei Xie, et al. ∙

research

∙ 01/29/2018

Stochastic Downsampling for Cost-Adjustable Inference and Improved Regularization in Convolutional Networks

It is desirable to train convolutional networks (CNNs) to run more effic...

1 Jason Kuen, et al. ∙

research

∙ 06/04/2017

CRNN: A Joint Neural Network for Redundancy Detection

This paper proposes a novel framework for detecting redundancy in superv...

0 Xinyu Fu, et al. ∙

research

∙ 05/27/2017

Fast MPEG-CDVS Encoder with GPU-CPU Hybrid Computing

The compact descriptors for visual search (CDVS) standard from ISO/IEC m...

0 Lingyu Duan, et al. ∙

research

∙ 08/03/2016

Learning Common and Specific Features for RGB-D Semantic Segmentation with Deconvolutional Networks

In this paper, we tackle the problem of RGB-D semantic segmentation of i...

0 Jinghua Wang, et al. ∙

Simon See

Featured Co-authors