Search Results for author:
Found 42 papers, 19 papers with code
XR-VLM: Cross-Relationship Modeling with Multi-part Prompts and Visual Features for Fine-Grained Recognition
To further enhance discriminative capability, we propose a cross relationship modeling pattern that combines visual feature with all class prompt features, enabling a deeper exploration of the relationships between these two modalities.
Robust Disentangled Counterfactual Learning for Physical Audiovisual Commonsense Reasoning
Furthermore, we introduce a counterfactual learning module to augment the model's reasoning ability by modeling physical knowledge relationships among different objects under counterfactual intervention.
Target-driven Self-Distillation for Partial Observed Trajectories Forecasting
This involves firstly training a fully observed model and then using a distillation process to create the final model.
Towards Robust Unsupervised Attention Prediction in Autonomous Driving
Robustly predicting attention regions of interest for self-driving systems is crucial for driving safety but presents significant challenges due to the labor-intensive nature of obtaining large-scale attention labels and the domain gap between self-driving scenarios and natural scenes.
A New Teacher-Reviewer-Student Framework for Semi-supervised 2D Human Pose Estimation
Secondly, we introduce a Multi-level Feature Learning strategy, which utilizes the outputs from different stages of the backbone to estimate the heatmap to guide network training, enriching the supervisory information while effectively capturing keypoint relationships.
Towards Balanced Continual Multi-Modal Learning in Human Pose Estimation
In this work, we introduce a novel balanced continual multi-modal learning method for 3D HPE, which harnesses the power of RGB, LiDAR, mmWave, and WiFi.
Action Quality Assessment via Hierarchical Pose-guided Multi-stage Contrastive Regression
Firstly, we introduce a multi-scale dynamic visual-skeleton encoder to capture fine-grained spatio-temporal visual and skeletal features.
Learning Group Interactions and Semantic Intentions for Multi-Object Trajectory Prediction
Effective modeling of group interactions and dynamic semantic intentions is crucial for forecasting behaviors like trajectories or movements.
Improving Batch Normalization with TTA for Robust Object Detection in Self-Driving
In current open real-world autonomous driving scenarios, challenges such as sensor failure and extreme weather conditions hinder the generalization of most autonomous driving perception models to these unseen domain due to the domain shifts between the test and training data.
T2SG: Traffic Topology Scene Graph for Topology Reasoning in Autonomous Driving
Understanding the traffic scenes and then generating high-definition (HD) maps present significant challenges in autonomous driving.
PITN: Physics-Informed Temporal Networks for Cuffless Blood Pressure Estimation
To tackle this challenge, we introduce a novel physics-informed temporal network~(PITN) with adversarial contrastive learning to enable precise BP estimation with very limited data.
Semi-Supervised Teacher-Reference-Student Architecture for Action Quality Assessment
Differing from the traditional teacher-student network, we propose a teacher-reference-student architecture to learn both unlabeled and labeled data, where the teacher network and the reference network are used to generate pseudo-labels for unlabeled data to supervise the student network.
Decomposed Vector-Quantized Variational Autoencoder for Human Grasp Generation
Generating realistic human grasps is a crucial yet challenging task for applications involving object manipulation in computer graphics and robotics.
Frequency-based Matcher for Long-tailed Semantic Segmentation
The successful application of semantic segmentation technology in the real world has been among the most exciting achievements in the computer vision community over the past decade.
NTIRE 2024 Quality Assessment of AI-Generated Content Challenge
A total of 196 participants have registered in the video track.
G3R: Generating Rich and Fine-grained mmWave Radar Data from 2D Videos for Generalized Gesture Recognition
Millimeter wave radar is gaining traction recently as a promising modality for enabling pervasive and privacy-preserving gesture recognition.
NTIRE 2024 Challenge on Short-form UGC Video Quality Assessment: Methods and Results
This paper reviews the NTIRE 2024 Challenge on Shortform UGC Video Quality Assessment (S-UGC VQA), where various excellent solutions are submitted and evaluated on the collected dataset KVQ from popular short-form video platform, i. e., Kuaishou/Kwai Platform.
SM4Depth: Seamless Monocular Metric Depth Estimation across Multiple Cameras and Scenes by One Model
Firstly, to obtain consistent depth across diverse scenes, we propose a novel metric scale modeling, i. e., variation-based unnormalized depth bins.
Region-Aware Exposure Consistency Network for Mixed Exposure Correction
Exposure correction aims to enhance images suffering from improper exposure to achieve satisfactory visual effects.
Learning Exposure Correction in Dynamic Scenes
Exposure correction aims to enhance visual data suffering from improper exposures, which can greatly improve satisfactory visual effects.
Mutual Distillation Learning For Person Re-Identification
With the rapid advancements in deep learning technologies, person re-identification (ReID) has witnessed remarkable performance improvements.
Uncovering the human motion pattern: Pattern Memory-based Diffusion Model for Trajectory Prediction
To uncover latent motion patterns in human behavior, we introduce a novel memory-based method, named Motion Pattern Priors Memory Network.
Multi-Stage Contrastive Regression for Action Quality Assessment
In recent years, there has been growing interest in the video-based action quality assessment (AQA).
Towards Efficient Object Re-Identification with A Novel Cloud-Edge Collaborative Framework
Object re-identification (ReID) is committed to searching for objects of the same identity across cameras, and its real-world deployment is gradually increasing.
Continuous Optical Zooming: A Benchmark for Arbitrary-Scale Image Super-Resolution in Real World
The extensive experiments demonstrate the superior performance of the arbitrary-scale SR models trained on the COZ dataset compared to models trained on simulated data.
VIoTGPT: Learning to Schedule Vision Tools in LLMs towards Intelligent Video Internet of Things
Video Internet of Things (VIoT) has shown full potential in collecting an unprecedented volume of video data.
Weakly-Supervised Temporal Action Localization by Inferring Salient Snippet-Feature
Weakly-supervised temporal action localization aims to locate action regions and identify action categories in untrimmed videos simultaneously by taking only video-level labels as the supervision.
Pseudo Label
Weakly-supervised Temporal Action Localization
+1
SGFormer: Semantic Graph Transformer for Point Cloud-based 3D Scene Graph Generation
In this paper, we propose a novel model called SGFormer, Semantic Graph TransFormer for point cloud-based 3D scene graph generation.
Unsupervised Self-Driving Attention Prediction via Uncertainty Mining and Knowledge Embedding
Predicting attention regions of interest is an important yet challenging task for self-driving systems.
Thinking Image Color Aesthetics Assessment: Models, Datasets and Benchmarks
We present a comprehensive study on a new task named image color aesthetics assessment (ICAA), which aims to assess color aesthetics based on human perception.
You Do Not Need Additional Priors or Regularizers in Retinex-Based Low-Light Image Enhancement
The Retinex-based methods require decomposing the image into reflectance and illumination components, which is a highly ill-posed problem and there is no available ground truth.
Dancing in the Dark: A Benchmark towards General Low-light Video Enhancement
To address this issue, we design a camera system and collect a high-quality low-light video dataset with multiple exposures and cameras.
Coarse-to-Fine Video Denoising with Dual-Stage Spatial-Channel Transformer
Meanwhile, we design a Multi-Scale Residual Structure to preserve multiple aspects of information at different stages, which contains a Temporal Features Aggregation Module to summarize the dynamic representation.
Learning to Help Emergency Vehicles Arrive Faster: A Cooperative Vehicle-Road Scheduling Approach
The ever-increasing heavy traffic congestion potentially impedes the accessibility of emergency vehicles (EVs), resulting in detrimental impacts on critical services and even safety of people's lives.
SPAP: Simultaneous Demand Prediction and Planning for Electric Vehicle Chargers in a New City
A direct idea is to leverage the urban transfer learning paradigm to learn the knowledge from a source city, then exploit it to predict charging demands, and meanwhile determine locations and amounts of slow/fast chargers for charging stations in the target city.
Language Guided Networks for Cross-modal Moment Retrieval
In this paper, we present Language Guided Networks (LGN), a new framework that leverages the sentence embedding to guide the whole process of moment retrieval.
A Real-time Action Representation with Temporal Encoding and Deep Compression
Our method achieves clear improvements on UCF101 action recognition benchmark against state-of-the-art real-time methods by 5. 4% in terms of accuracy and 2 times faster in terms of inference speed with a less than 5MB storage model.
MemNet: Memory-Efficiency Guided Neural Architecture Search with Augment-Trim learning
Recent studies on automatic neural architectures search have demonstrated significant performance, competitive to or even better than hand-crafted neural architectures.
PVSS: A Progressive Vehicle Search System for Video Surveillance Networks
In this paper, a Progressive Vehicle Search System, named as PVSS, is designed to solve the above problems.
Multi-Granularity Reasoning for Social Relation Recognition from Images
To bridge the domain gap, we propose a Multi-Granularity Reasoning framework for social relation recognition from images.
Ranked #3 on
Visual Social Relationship Recognition
on PISC
KTAN: Knowledge Transfer Adversarial Network
To transfer the knowledge of intermediate representations, we set high-level teacher feature maps as a target, toward which the student feature maps are trained.
Generalized Zero-Shot Learning for Action Recognition with Web-Scale Video Data
Motivated by this, we study the task of action recognition in surveillance video under a more realistic \emph{generalized zero-shot setting}, where testing data contains both seen and unseen classes.
