67 citations · 127 across the 17 of their papers we have counts for
17 papers
Motion-I2V: Consistent and Controllable Image-to-Video Generation with Explicit Motion Modeling
Xiaoyu Shi, Zhaoyang Huang, Fu-Yun Wang +9
We introduce Motion-I2V, a novel framework for consistent and controllable image-to-video generation (I2V). In contrast to previous methods that directly learn the complicated imag…
Resilient Practical Test-Time Adaptation: Soft Batch Normalization Alignment and Entropy-driven Memory Bank
Xingzhi Zhou, Zhiliang Tian, Ka Chun Cheung +2
Test-time domain adaptation effectively adjusts the source domain model to accommodate unseen domain shifts in a target domain during inference. However, the model performance can…
CopyRNeRF: Protecting the CopyRight of Neural Radiance Fields
Ziyuan Luo, Qing Guo, Ka Chun Cheung +2
Neural Radiance Fields (NeRF) have the potential to be a major representation of media. Since training a NeRF has never been an easy task, the protection of its model copyright sho…
TrajectoryFormer: 3D Object Tracking Transformer with Predictive Trajectory Hypotheses
Xuesong Chen, Shaoshuai Shi, Chao Zhang +5
3D multi-object tracking (MOT) is vital for many applications including autonomous driving vehicles and service robots. With the commonly used tracking-by-detection paradigm, 3D MO…
FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation
Xiaoyu Shi, Zhaoyang Huang, Dasong Li +6
FlowFormer introduces a transformer architecture into optical flow estimation and achieves state-of-the-art performance. The core component of FlowFormer is the transformer-based c…
VideoFlow: Exploiting Temporal Cues for Multi-frame Optical Flow Estimation
Xiaoyu Shi, Zhaoyang Huang, Weikang Bian +7
We introduce VideoFlow, a novel optical flow estimation framework for videos. In contrast to previous methods that learn to estimate optical flow from two frames, VideoFlow concurr…
Adaptive Label Smoothing with Self-Knowledge in Natural Language Generation
Dongkyu Lee, Ka Chun Cheung, Nevin L. Zhang
Overconfidence has been shown to impair generalization and calibration of a neural network. Previous studies remedy this issue by adding a regularization term to a loss function, p…
Hard Gate Knowledge Distillation -- Leverage Calibration for Robust and Reliable Language Model
Dongkyu Lee, Zhiliang Tian, Yingxiu Zhao +2
In knowledge distillation, a student model is trained with supervisions from both knowledge from a teacher and observations drawn from a training data distribution. Knowledge of a…
NeuralMarker: A Framework for Learning General Marker Correspondence
Zhaoyang Huang, Xiaokun Pan, Weihong Pan +5
We tackle the problem of estimating correspondences from a general marker, such as a movie poster, to an image that captures such a marker. Conventionally, this problem is addresse…
Learning Degradation Representations for Image Deblurring
Dasong Li, Yi Zhang, Ka Chun Cheung +3
In various learning-based image restoration tasks, such as image denoising and image super-resolution, the degradation representations were widely used to model the degradation pro…
NVIDIA-UNIBZ Submission for EPIC-KITCHENS-100 Action Anticipation Challenge 2022
Tsung-Ming Tai, Oswald Lanz, Giuseppe Fiameni +5
In this report, we describe the technical details of our submission for the EPIC-Kitchen-100 action anticipation challenge. Our modelings, the higher-order recurrent space-time tra…
A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
Dasong Li, Xiaoyu Shi, Yi Zhang +5
Video restoration, which aims to restore clear frames from degraded videos, has numerous important applications. The key to video restoration depends on utilizing inter-frame infor…
MPPNet: Multi-Frame Feature Intertwining with Proxy Points for 3D Temporal Object Detection
Xuesong Chen, Shaoshuai Shi, Benjin Zhu +3
Accurate and reliable 3D detection is vital for many applications including autonomous driving vehicles and service robots. In this paper, we present a flexible and high-performanc…
FlowFormer: A Transformer Architecture for Optical Flow
Zhaoyang Huang, Xiaoyu Shi, Chao Zhang +5
We introduce optical Flow transFormer, dubbed as FlowFormer, a transformer-based neural network architecture for learning optical flow. FlowFormer tokenizes the 4D cost volume buil…
LIFE: Lighting Invariant Flow Estimation
Zhaoyang Huang, Xiaokun Pan, Runsen Xu +4
We tackle the problem of estimating flow between two images with large lighting variations. Recent learning-based flow estimation frameworks have shown remarkable performance on im…
Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
Yixiao Ge, Xiao Zhang, Ching Lam Choi +6
The recent studies of knowledge distillation have discovered that ensembling the "dark knowledge" from multiple teachers or students contributes to creating better soft targets for…
Understanding Top-k Sparsification in Distributed Deep Learning
Shaohuai Shi, Xiaowen Chu, Ka Chun Cheung +1
Distributed stochastic gradient descent (SGD) algorithms are widely deployed in training large-scale deep learning models, while the communication overhead among workers becomes th…