Search Results for author:
Found 48 papers, 15 papers with code
A Comprehensive Study of Weight Sharing in Graph Networks for 3D Human Pose Estimation
The objective of this paper is to have a comprehensive and systematic study of weight sharing in GCNs for 3D HPE.
What Large Language Models Bring to Text-rich VQA?
This pipeline achieved superior performance compared to the majority of existing Multimodal Large Language Models (MLLM) on four text-rich VQA datasets.
RigLSTM: Recurrent Independent Grid LSTM for Generalizable Sequence Learning
Sequential processes in real-world often carry a combination of simple subsystems that interact with each other in certain forms.
LaplaceConfidence: a Graph-based Approach for Learning with Noisy Labels
We introduce LaplaceConfidence, a method that to obtain label confidence (i. e., clean probabilities) utilizing the Laplacian energy.
Deeply Coupled Cross-Modal Prompt Learning
Recent advancements in multimodal foundation models (e. g., CLIP) have excelled in zero-shot generalization.
Performative Prediction with Bandit Feedback: Learning through Reparameterization
Specifically, we develop a {\em reparameterization} framework that reparametrizes the performative prediction objective as a function of the induced data distribution.
Vehicle Sequencing at Signal-Free Intersections: Analytical Performance Guarantees Based on PDMP Formulation
Signal-free intersections are a representative application of smart and connected vehicle technologies.
MotionTrack: Learning Robust Short-term and Long-term Motions for Multi-Object Tracking
For dense crowds, we design a novel Interaction Module to learn interaction-aware motions from short-term trajectories, which can estimate the complex movement of each target.
A Global and Patch-wise Contrastive Loss for Accurate Automated Exudate Detection
In this paper, we propose a loss function that incorporates a global segmentation loss, a patch-wise density loss, and a patch-wise edge-aware loss to improve the performance of these networks on the detection and segmentation of hard exudates.
Learning from Noisy Pseudo Labels for Semi-Supervised Temporal Action Localization
To this end, we propose a unified framework, termed Noisy Pseudo-Label Learning, to handle both location biases and category errors.
Multi-Instance Partial-Label Learning: Towards Exploiting Dual Inexact Supervision
MIPLGP first assigns each instance with a candidate label set in an augmented label space, then transforms the candidate label set into a logarithmic space to yield the disambiguated and continuous labels via an exclusive disambiguation strategy, and last induces a model based on the Gaussian processes.
Be Careful with Rotation: A Uniform Backdoor Pattern for 3D Shape
As a result, backdoor pattern designed for one certain 3D data structure will be disable for other data structures of the same 3D scene.
Global Meets Local: Effective Multi-Label Image Classification via Category-Aware Weak Supervision
This paper builds a unified framework to perform effective noisy-proposal suppression and to interact between global and local features for robust feature learning.
Fully Digital Second-order Level-crossing Sampling ADC for Data Saving in Sensing Sparse Signals
This paper presents a fully integrated second-order level-crossing sampling data converter for real-time data compression and feature extraction.
Dynamic Predictive Sampling Analog to Digital Converter for Sparse Signal Sensing
No quantization is performed for successfully predicted sampling points so that the data throughput and power can be saved.
UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction
Relational triple extraction is challenging for its difficulty in capturing rich correlations between entities and relations.
Ranked #1 on
Relation Extraction
on WebNLG
LACV-Net: Semantic Segmentation of Large-Scale Point Cloud Scene via Local Adaptive and Comprehensive VLAD
Meanwhile, it is difficult for networks to capture global information in large-scale distributed contexts.
Learning to Refactor Action and Co-occurrence Features for Temporal Action Localization
The main challenge of Temporal Action Localization is to retrieve subtle human actions from various co-occurring ingredients, e. g., context and background, in an untrimmed video.
Online Bayesian Recommendation with No Regret
For each user with her own private preference and belief, the platform commits to a recommendation strategy to utilize his information advantage on the product state to persuade the self-interested user to follow the recommendation.
Time-aware Path Reasoning on Knowledge Graph for Recommendation
In this work, we propose a novel Time-aware Path reasoning for Recommendation (TPRec for short) method, which leverages the potential of temporal information to offer better recommendation with plausible explanations.
Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction
Specifically, the proposed unlimited neighborhood interaction module generates the fused-features of all agents involved in an interaction simultaneously, which is adaptive to any number of agents and any range of interaction area.
Enriching Local and Global Contexts for Temporal Action Localization
We explore two existing models to be the P-Net in our experiments.
Exploit Visual Dependency Relations for Semantic Segmentation
Inter-class reasoning then performs spatial and semantic reasoning based on the dependency relations among different object categories.
Optimal Query Complexity of Secure Stochastic Convex Optimization
The goal of the learner is to optimize the accuracy, i. e., obtaining an accurate estimate of the optimal point, while securing her privacy, i. e., making it difficult for the adversary to infer the optimal point.
Weakly Supervised Temporal Action Localization Through Learning Explicit Subspaces for Action and Context
To address this challenge, we introduce a framework that learns two feature subspaces respectively for actions and their context.
Action Recognition
Weakly-supervised Temporal Action Localization
+1
ACSNet: Action-Context Separation Network for Weakly Supervised Temporal Action Localization
In this paper, we introduce an Action-Context Separation Network (ACSNet) that explicitly takes into account context for accurate action localization.
Ranked #7 on
Weakly Supervised Action Localization
on THUMOS’14
Video Polyp Segmentation
Weakly Supervised Action Localization
+2
Density-aware Haze Image Synthesis by Self-Supervised Content-Style Disentanglement
The key procedure of haze image translation through adversarial training lies in the disentanglement between the feature only involved in haze synthesis, i. e. style feature, and the feature representing the invariant semantic content, i. e. content feature.
Competitive Information Design for Pandora's Box
We study a natural competitive-information-design variant for the Pandora's Box problem (Weitzman 1979), where each box is associated with a strategic information sender who can design what information about the box's prize value to be revealed to the agent when the agent inspects the box.
Computer Science and Game Theory
Modulated Graph Convolutional Network for 3D Human Pose Estimation
It consists of two main components: weight modulation and affinity modulation.
Ranked #37 on
3D Human Pose Estimation
on MPI-INF-3DHP
(AUC metric)
Meta Pairwise Relationship Distillation for Unsupervised Person Re-Identification
Unsupervised person re-identification (Re-ID) remains challenging due to the lack of ground-truth labels.
Two-Stream Appearance Transfer Network for Person Image Generation
It is a multi-stage architecture consisting of a source stream and a target stream.
Two-Stream Consensus Network for Weakly-Supervised Temporal Action Localization
Weakly-supervised Temporal Action Localization (W-TAL) aims to classify and localize all action instances in an untrimmed video under only video-level supervision.
Ranked #11 on
Weakly Supervised Action Localization
on THUMOS14
Vocal Bursts Valence Prediction
Weakly Supervised Action Localization
+2
Addressing Class Imbalance in Scene Graph Parsing by Learning to Contrast and Score
Motivated by the fact that detecting these rare relations can be critical in real-world applications, this paper introduces a novel integrated framework of classification and ranking to resolve the class imbalance problem in scene graph parsing.
The 1st Tiny Object Detection Challenge:Methods and Results
The 1st Tiny Object Detection (TOD) Challenge aims to encourage research in developing novel and accurate methods for tiny object detection in images which have wide views, with a current focus on tiny person detection.
Multi-label Zero-shot Classification by Learning to Transfer from External Knowledge
On the other hand, there is a large semantic gap between seen and unseen classes in the existing multi-label classification datasets.
FGRec: A Fine-Grained Point-of-Interest Recommendation Framework by Capturing Intrinsic Influences
Recent studies mainly utilize social information, categorical information and/or geographical information to supplement the highly sparse check-in data.
Continuous matrix product operator approach to finite temperature quantum states
We present an algorithm for studying quantum systems at finite temperature using continuous matrix product operator representation.
Strongly Correlated Electrons Statistical Mechanics Computational Physics
Combining Visible Light and Infrared Imaging for Efficient Detection of Respiratory Infections such as COVID-19 on Portable Device
In this work, we perform the health screening through the combination of the RGB and thermal videos obtained from the dual-mode camera and deep learning architecture. We first accomplish a respiratory data capture technique for people wearing masks by using face recognition.
Bandit Learning with Delayed Impact of Actions
In this paper, we formulate this delayed and long-term impact of actions within the context of multi-armed bandits.
Does Learning Specific Features for Related Parts Help Human Pose Estimation?
Can we identify related parts and learn specific features for them to improve pose estimation?
A Compositional Textual Model for Recognition of Imperfect Word Images
Printed text recognition is an important problem for industrial OCR systems.
Optical Character Recognition (OCR)
Printed Text Recognition
MsCGAN: Multi-scale Conditional Generative Adversarial Networks for Person Image Generation
One generator transforms the conditional person image into a coarse image of the target pose globally, and the other is to enhance the detailed quality of the synthetic person image through a local reinforcement network.
Deeply Learned Compositional Models for Human Pose Estimation
This results in a network with a hierarchical compositional architecture and bottom-up/top-down inference stages.
Ranked #11 on
Pose Estimation
on MPII Human Pose
Next Check-ins Prediction via History and Friendship on Location-Based Social Networks
In this paper, we propose a unified location prediction framework to integrate the effect of history check-in and the influence of social circles.
ReabsNet: Detecting and Revising Adversarial Examples
Though deep neural network has hit a huge success in recent studies and applica- tions, it still remains vulnerable to adversarial perturbations which are imperceptible to humans.
Efficient Online Local Metric Adaptation via Negative Samples for Person Re-Identification
In contrast to these methods, this paper advocates a different paradigm: part of the learning can be performed online but with nominal costs, so as to achieve online metric adaptation for different input probes.
Towards a Unified Compositional Model for Visual Pattern Modeling
Compositional models represent visual patterns as hierarchies of meaningful and reusable parts.
A 20-Liter Test Stand with Gas Purification for Liquid Argon Research
We describe the design of a 20-liter test stand constructed to study fundamental properties of liquid argon (LAr).
Instrumentation and Detectors High Energy Physics - Experiment
