Search Results for author:
Found 45 papers, 21 papers with code
UFO²: A Unified Framework towards Omni-supervised Object Detection
Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive image-level tags.
ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals
To cope with these difficulties, this paper proposes a novel agent-centric model with anchor-informed proposals for efficient multimodal motion prediction.
SportsTrack: An Innovative Method for Tracking Athletes in Sports Scenes
The SportsMOT dataset aims to solve multiple object tracking of athletes in different sports scenes such as basketball or soccer.
QML for Argoverse 2 Motion Forecasting Challenge
To safely navigate in various complex traffic scenarios, autonomous driving systems are generally equipped with a motion forecasting module to provide vital information for the downstream planning module.
Normalized/Clipped SGD with Perturbation for Differentially Private Non-Convex Optimization
By ensuring differential privacy in the learning algorithms, one can rigorously mitigate the risk of large models memorizing sensitive training data.
TL-GAN: Improving Traffic Light Recognition via Data Synthesis for Autonomous Driving
Traffic light recognition, as a critical component of the perception module of self-driving vehicles, plays a vital role in the intelligent transportation systems.
Attribute Descent: Simulating Object-Centric Datasets on the Content Level and Beyond
This article aims to use graphic engines to simulate a large number of training data that have free annotations and possibly strongly resemble to real-world data.
Learning Intrinsic Images for Clothing
A more interpretable edge-aware metric and an annotation scheme is designed for the testing set, which allows diagnostic evaluation for intrinsic models.
Exploring Simple 3D Multi-Object Tracking for Autonomous Driving
3D multi-object tracking in LiDAR point clouds is a key ingredient for self-driving vehicles.
Neural Network Repair with Reachability Analysis
Formally verifying the safety and robustness of well-trained DNNs and learning-enabled systems under attacks, model uncertainties, and sensing errors is essential for safe autonomy.
Reachability Analysis of Convolutional Neural Networks
Besides the computation of reachable sets, our approach is also capable of backtracking to the input domain given an output reachable set.
Self-Supervised Pillar Motion Learning for Autonomous Driving
Autonomous driving can benefit from motion behavior comprehension when interacting with diverse traffic participants in highly dynamic environments.
Robust Dynamical Decoupling for the Manipulation of a Spin Network via a Single Spin
High-fidelity control of quantum systems is crucial for quantum information processing, but is often limited by perturbations from the environment and imperfections in the applied control fields.
Quantum Physics
Network-Constrained Transactive Control for Multi- Microgrids-based Distribution Networks with SOPs
Different from most transactive control studies only focusing on economic aspect, this paper develops a novel network-constrained transactive control (NTC) framework that can address both economic and secure issues for a multi-microgrids-based distribution network considering uncertainties.
Optimization and Control
UFO$^2$: A Unified Framework towards Omni-supervised Object Detection
Existing work on object detection often relies on a single form of annotation: the model is trained using either accurate yet costly bounding boxes or cheaper but less expressive image-level tags.
Hierarchical Contrastive Motion Learning for Video Action Recognition
Thus, the motion features at higher levels are trained to gradually capture semantic dynamics and evolve more discriminative for action recognition.
Joint Disentangling and Adaptation for Cross-Domain Person Re-Identification
To this end, we propose a joint learning framework that disentangles id-related/unrelated features and enforces adaptation to work on the id-related feature space exclusively.
Ranked #6 on
Unsupervised Domain Adaptation
on Market to MSMT
Contrastive Learning for Weakly Supervised Phrase Grounding
Given pairs of images and captions, we maximize compatibility of the attention-weighted regions and the words in the corresponding caption, compared to non-corresponding pairs of images and captions.
PAMTRI: Pose-Aware Multi-Task Learning for Vehicle Re-Identification Using Highly Randomized Synthetic Data
In comparison with person re-identification (ReID), which has been widely studied in the research community, vehicle ReID has received less attention.
Reachable Set Estimation for Neural Network Control Systems: A Simulation-Guided Approach
Then, in combination with reachability methods developed for various dynamical system classes modeled by ordinary differential equations, a recursive algorithm is developed for over-approximating the reachable set of the closed-loop system.
NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems
For learning-enabled CPS, such as closed-loop control systems incorporating neural networks, NNV provides exact and over-approximate reachability analysis schemes for linear plant models and FFNN controllers with piecewise-linear activation functions, such as ReLUs.
Instance-aware, Context-focused, and Memory-efficient Weakly Supervised Object Detection
Weakly supervised learning has emerged as a compelling tool for object detection by reducing the need for strong supervision during training.
Ranked #1 on
Weakly Supervised Object Detection
on COCO test-dev
Reachability Analysis for Feed-Forward Neural Networks using Face Lattices
To address this challenge, we propose a parallelizable technique to compute exact reachable sets of a neural network to an input set.
FOCUS: Dealing with Label Quality Disparity in Federated Learning
It maintains a small set of benchmark samples on the FL server and quantifies the credibility of the client local data without directly observing them by computing the mutual cross-entropy between performance of the FL model on the local datasets and that of the client local FL model on the benchmark dataset.
Robust Multimodal Image Registration Using Deep Recurrent Reinforcement Learning
To this end, these two components are tackled in an end-to-end manner via reinforcement learning in this work.
Simulating Content Consistent Vehicle Datasets with Attribute Descent
Between synthetic and real data, there is a two-level domain gap, i. e., content level and appearance level.
Dancing to Music
In the analysis phase, we decompose a dance into a series of basic dance units, through which the model learns how to move.
Ranked #3 on
Motion Synthesis
on BRACE
A Delay Metric for Video Object Detection: What Average Precision Fails to Tell
Average precision (AP) is a widely used metric to evaluate detection accuracy of image and video object detectors.
Rethinking Full Connectivity in Recurrent Neural Networks
We study structurally sparse RNNs, showing that they are well suited for acceleration on parallel hardware, with a greatly reduced cost of the recurrent operations as well as orders of magnitude less recurrent weights.
STEP: Spatio-Temporal Progressive Learning for Video Action Detection
In this paper, we propose Spatio-TEmporal Progressive (STEP) action detector---a progressive learning framework for spatio-temporal action detection in videos.
Ranked #2 on
Action Detection
on UCF101-24
Joint Discriminative and Generative Learning for Person Re-identification
To this end, we propose a joint learning framework that couples re-id learning and data generation end-to-end.
Ranked #1 on
Person Re-Identification
on UAV-Human
Image-to-Image Translation
Unsupervised Domain Adaptation
+1
CityFlow: A City-Scale Benchmark for Multi-Target Multi-Camera Vehicle Tracking and Re-Identification
Urban traffic optimization using traffic cameras as sensors is driving the need to advance state-of-the-art multi-target multi-camera (MTMC) tracking.
Discovering Spatio-Temporal Action Tubes
In this paper, we address the challenging problem of spatial and temporal action detection in videos.
Self-Supervised Spatiotemporal Feature Learning via Video Rotation Prediction
The success of deep neural networks generally requires a vast amount of training data to be labeled, which is expensive and unfeasible in scale, especially for video collections.
Ranked #39 on
Self-Supervised Action Recognition
on HMDB51
Self-Supervised Action Recognition
Temporal Action Localization
+1
Verification for Machine Learning, Autonomy, and Neural Networks Survey
This survey presents an overview of verification techniques for autonomous systems, with a focus on safety-critical autonomous cyber-physical systems (CPS) and subcomponents thereof.
Models Matter, So Does Training: An Empirical Study of CNNs for Optical Flow Estimation
We investigate two crucial and closely related aspects of CNNs for optical flow estimation: models and training.
Ranked #4 on
Optical Flow Estimation
on KITTI 2012
Making Convolutional Networks Recurrent for Visual Sequence Learning
Recurrent neural networks (RNNs) have emerged as a powerful model for a broad range of machine learning problems that involve sequential data.
Budget-Aware Activity Detection with A Recurrent Policy Network
In this paper, we address the challenging problem of efficient temporal activity detection in untrimmed long videos.
PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volume
It then uses the warped features and features of the first image to construct a cost volume, which is processed by a CNN to estimate the optical flow.
Ranked #3 on
Dense Pixel Correspondence Estimation
on HPatches
Dense Pixel Correspondence Estimation
Optical Flow Estimation
MoCoGAN: Decomposing Motion and Content for Video Generation
The proposed framework generates a video by mapping a sequence of random vectors to a sequence of video frames.
Dynamic Facial Analysis: From Bayesian Filtering to Recurrent Neural Network
We are inspired by the fact that the computation performed in an RNN bears resemblance to Bayesian filters, which have been used for tracking in many previous methods for facial analysis from videos.
Ranked #1 on
Head Pose Estimation
on BIWI
(MAE (trained with BIWI data) metric, using extra
training data)
Online Detection and Classification of Dynamic Hand Gestures With Recurrent 3D Convolutional Neural Network
Automatic detection and classification of dynamic hand gestures in real-world systems intended for human computer interaction is challenging as: 1) there is a large diversity in how people perform gestures, making detection and classification difficult; 2) the system must work online in order to avoid noticeable lag between performing a gesture and its classification; in fact, a negative lag (classification before the gesture is finished) is desirable, as feedback to the user can then be truly instantaneous.
Super Normal Vector for Activity Recognition Using Depth Sequences
This paper presents a new framework for human activity recognition from video sequences captured by a depth camera.
