Search Results for author:
Found 66 papers, 22 papers with code
Semi-Supervised Unconstrained Head Pose Estimation in the Wild
Existing head pose estimation datasets are either composed of numerous samples by non-realistic synthesis or lab collection, or limited images by labor-intensive annotating.
Learning Multiple Representations with Inconsistency-Guided Detail Regularization for Mask-Guided Matting
Our framework and model introduce the following key aspects: (1) to learn real-world adaptive semantic representation for objects with diverse and complex structures under real-world scenes, we introduce extra semantic segmentation and edge detection tasks on more diverse real-world data with segmentation annotations; (2) to avoid overfitting on low-level details, we propose a module to utilize the inconsistency between learned segmentation and matting representations to regularize detail refinement; (3) we propose a novel background line detection task into our auxiliary learning framework, to suppress interference of background lines or textures.
View-Centric Multi-Object Tracking with Homographic Matching in Moving UAV
In this paper, we address the challenge of multi-object tracking (MOT) in moving Unmanned Aerial Vehicle (UAV) scenarios, where irregular flight trajectories, such as hovering, turning left/right, and moving up/down, lead to significantly greater complexity compared to fixed-camera MOT.
YOLO-MED : Multi-Task Interaction Network for Biomedical Images
Object detection and semantic segmentation are pivotal components in biomedical image analysis.
Task Indicating Transformer for Task-conditional Dense Predictions
The task-conditional model is a distinctive stream for efficient multi-task learning.
Federated Multi-Task Learning on Non-IID Data Silos: An Experimental Study
The innovative Federated Multi-Task Learning (FMTL) approach consolidates the benefits of Federated Learning (FL) and Multi-Task Learning (MTL), enabling collaborative model training on multi-task learning datasets.
Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency Training
The 2D human pose estimation (HPE) is a basic visual problem.
Enhancing cross-domain detection: adaptive class-aware contrastive transformer
Recently, the detection transformer has gained substantial attention for its inherent minimal post-processing requirement. However, this paradigm relies on abundant training data, yet in the context of the cross-domain adaptation, insufficient labels in the target domain exacerbate issues of class imbalance and model performance degradation. To address these challenges, we propose a novel class-aware cross domain detection transformer based on the adversarial learning and mean-teacher framework. First, considering the inconsistencies between the classification and regression tasks, we introduce an IoU-aware prediction branch and exploit the consistency of classification and location scores to filter and reweight pseudo labels. Second, we devise a dynamic category threshold refinement to adaptively manage model confidence. Third, to alleviate the class imbalance, an instance-level class-aware contrastive learning module is presented to encourage the generation of discriminative features for each class, particularly benefiting minority classes. Experimental results across diverse domain-adaptive scenarios validate our method's effectiveness in improving performance and alleviating class imbalance issues, which outperforms the state-of-the-art transformer based methods.
PA-SAM: Prompt Adapter SAM for High-Quality Image Segmentation
In this paper, we introduce a novel prompt-driven adapter into SAM, namely Prompt Adapter Segment Anything Model (PA-SAM), aiming to enhance the segmentation mask quality of the original SAM.
ChangeNet: Multi-Temporal Asymmetric Change Detection Dataset
The ChangeNet dataset is suitable for both binary change detection (BCD) and semantic change detection (SCD) tasks.
FedHCA$^2$: Towards Hetero-Client Federated Multi-Task Learning
Moreover, we employ learnable Hyper Aggregation Weights for each client to customize personalized parameter updates.
Combining Past, Present and Future: A Self-Supervised Approach for Class Incremental Learning
In detail, CPPF consists of a prototype clustering module (PC), an embedding space reserving module (ESR) and a multi-teacher distillation module (MTD).
UNIDEAL: Curriculum Knowledge Distillation Federated Learning
Federated Learning (FL) has emerged as a promising approach to enable collaborative learning among multiple clients while preserving data privacy.
Prompt Guided Transformer for Multi-Task Dense Prediction
Task-conditional architecture offers advantage in parameter efficiency but falls short in performance compared to state-of-the-art multi-decoder methods.
Guided Patch-Grouping Wavelet Transformer with Spatial Congruence for Ultra-High Resolution Segmentation
For the sake of high inference speed and low computation complexity, $\mathcal{T}$ partitions the original UHR image into patches and groups them dynamically, then learns the low-level local details with the lightweight multi-head Wavelet Transformer (WFormer) network.
Contrast, Stylize and Adapt: Unsupervised Contrastive Learning Framework for Domain Adaptive Semantic Segmentation
To address this, we present CONtrastive FEaTure and pIxel alignment (CONFETI) for bridging the domain gap at both the pixel and feature levels using a unique contrastive formulation.
Ultra-High Resolution Segmentation with Ultra-Rich Context: A Novel Benchmark
With the increasing interest and rapid development of methods for Ultra-High Resolution (UHR) segmentation, a large-scale benchmark covering a wide range of scenes with full fine-grained dense annotations is urgently needed to facilitate the field.
Ranked #1 on
Semantic Segmentation
on INRIA Aerial Image Labeling
(mIOU metric)
Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation
Existing knowledge distillation works for semantic segmentation mainly focus on transferring high-level contextual knowledge from teacher to student.
BPJDet: Extended Object Representation for Generic Body-Part Joint Detection
In this paper, we focus on the joint detection of human body and its parts.
DirectMHP: Direct 2D Multi-Person Head Pose Estimation with Full-range Angles
We present comprehensive comparisons with state-of-the-art single HPE methods on public benchmarks, as well as superior baseline results on our constructed MPHPE datasets.
T2M-GPT: Generating Human Motion from Textual Descriptions with Discrete Representations
Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach.
Ranked #11 on
Motion Synthesis
on HumanML3D
Generating Human Motion From Textual Descriptions With Discrete Representations
Additionally, we conduct analyses on HumanML3D and observe that the dataset size is a limitation of our approach.
A Simple Framework for Text-Supervised Semantic Segmentation
LoDA and SimSeg jointly ameliorate a vanilla CLIP to produce impressive semantic segmentation results.
Body-Part Joint Detection and Association via Extended Object Representation
This paper focuses on the problem of joint detection of human body and its corresponding parts.
An Intuitive and Unconstrained 2D Cube Representation for Simultaneous Head Detection and Pose Estimation
Most recent head pose estimation (HPE) methods are dominated by the Euler angle representation.
Ranked #8 on
Head Pose Estimation
on BIWI
(MAE (trained with BIWI data) metric)
EDEN: A Plug-in Equivariant Distance Encoding to Beyond the 1-WL Test
While most existing message-passing graph neural networks (MPNNs) are permutation-invariant in graph-level representation learning and permutation-equivariant in node- and edge-level representation learning, their expressive power is commonly limited by the 1-Weisfeiler-Lehman (1-WL) graph isomorphism test.
StuArt: Individualized Classroom Observation of Students with Automatic Behavior Recognition and Tracking
In this paper, we present StuArt, a novel automatic system designed for the individualized classroom observation, which empowers instructors to concern the learning status of each student.
SSDA-YOLO: Semi-supervised Domain Adaptive YOLO for Cross-Domain Object Detection
Domain adaptive object detection (DAOD) aims to alleviate transfer performance degradation caused by the cross-domain discrepancy.
Position-Aware Subgraph Neural Networks with Data-Efficient Learning
2) Prevailing graph augmentation methods for GEL, including rule-based, sample-based, adaptive, and automated methods, are not suitable for augmenting subgraphs because a subgraph contains fewer nodes but richer information such as position, neighbor, and structure.
Completely Heterogeneous Federated Learning
Federated learning (FL) faces three major difficulties: cross-domain, heterogeneous models, and non-i. i. d.
Joint Multi-Person Body Detection and Orientation Estimation via One Unified Embedding
In the paper, we propose a single-stage end-to-end trainable framework for tackling the HBOE problem with multi-persons.
NoMorelization: Building Normalizer-Free Models from a Sample's Perspective
The normalizing layer has become one of the basic configurations of deep learning models, but it still suffers from computational inefficiency, interpretability difficulties, and low generality.
Cooperative Self-Training for Multi-Target Adaptive Semantic Segmentation
In this work we address multi-target domain adaptation (MTDA) in semantic segmentation, which consists in adapting a single model from an annotated source dataset to multiple unannotated target datasets that differ in their underlying data distributions.
Degradation-Guided Meta-Restoration Network for Blind Super-Resolution
The extractor estimates the degradations in LR inputs and guides the meta-restoration modules to predict restoration parameters for different degradations on-the-fly.
RAFT-MSF: Self-Supervised Monocular Scene Flow using Recurrent Optimizer
Self-supervised methods demonstrate learning scene flow estimation from unlabeled data, yet their accuracy lags behind (semi-)supervised methods.
Reinforcing Local Feature Representation for Weakly-Supervised Dense Crowd Counting
To address this problem, we propose a self-adaptive feature similarity learning (SFSL) network and a global-local consistency (GLC) loss to reinforce local feature representation.
Student Dangerous Behavior Detection in School
Video surveillance systems have been installed to ensure the student safety in schools.
Trimap-guided Feature Mining and Fusion Network for Natural Image Matting
For emerging content-based feature fusion, most existing matting methods only focus on local features which lack the guidance of a global feature with strong semantic information related to the interesting object.
Ranked #4 on
Image Matting
on Composition-1K
FreqNet: A Frequency-domain Image Super-Resolution Network with Dicrete Cosine Transform
A specialized pipeline is designed, and we further propose a frequency loss function to fit the nature of our frequency-domain task.
PANet: Perspective-Aware Network with Dynamic Receptive Fields and Self-Distilling Supervision for Crowd Counting
Crowd counting aims to learn the crowd density distributions and estimate the number of objects (e. g. persons) in images.
Adversarial and Contrastive Variational Autoencoder for Sequential Recommendation
To solve the above problem, in this work, we propose a novel method called Adversarial and Contrastive Variational Autoencoder (ACVAE) for sequential recommendation.
Temporal Continuity Based Unsupervised Learning for Person Re-Identification
Most existing person re-id methods generally require a large amount of identity labeled data to act as discriminative guideline for representation learning.
Learning Texture Transformer Network for Image Super-Resolution
In this paper, we propose a novel Texture Transformer Network for Image Super-Resolution (TTSR), in which the LR and Ref images are formulated as queries and keys in a transformer, respectively.
LRNNet: A Light-Weighted Network with Efficient Reduced Non-Local Operation for Real-Time Semantic Segmentation
Many of these applications need to perform a real-time and efficient prediction for semantic segmentation with a light-weighted network.
Hierarchical Opacity Propagation for Image Matting
Natural image matting is a fundamental problem in computational photography and computer vision.
Show, Recall, and Tell: Image Captioning with Recall Mechanism
SG and RWS are de-signed for the best use of recalled words.
Natural Image Matting via Guided Contextual Attention
Inspired by affinity-based method and the successes of contextual attention in inpainting, we develop a novel end-to-end approach for natural image matting with a guided contextual attention module, which is specifically designed for image matting.
Inductive Guided Filter: Real-time Deep Image Matting with Weakly Annotated Masks on Mobile Devices
A high efficient image matting method based on a weakly annotated mask is in demand for mobile applications.
FH-GAN: Face Hallucination and Recognition using Generative Adversarial Network
One of the most important problem is low resolution face images which can result in bad performance on face recognition.
Spatial Shortcut Network for Human Pose Estimation
Like many computer vision problems, human pose estimation is a challenging problem in that recognizing a body part requires not only information from local area but also from areas with large spatial distance.
Rethinking on Multi-Stage Networks for Human Pose Estimation
Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods.
Ranked #1 on
Pose Estimation
on COCO minival
Attend More Times for Image Captioning
Most attention-based image captioning models attend to the image once per word.
An Adversarial Approach to Hard Triplet Generation
While deep neural networks have demonstrated competitive results for many visual recognition and image retrieval tasks, the major challenge lies in distinguishing similar images from different categories (i. e., hard negative examples) while clustering images with large variations from the same category (i. e., hard positive examples).
Supervised Hashing based on Energy Minimization
Recently, supervised hashing methods have attracted much attention since they can optimize retrieval speed and storage cost while preserving semantic information.
Bayesian Supervised Hashing
To address this problem, we present a novel fully Bayesian treatment for supervised hashing problem, named Bayesian Supervised Hashing (BSH), in which hyperparameters are automatically tuned during optimization.
Efficient Two-Dimensional Sparse Coding Using Tensor-Linear Combination
Sparse coding (SC) is an automatic feature extraction and selection technique that is widely used in unsupervised learning.
Graph Regularized Tensor Sparse Coding for Image Representation
Sparse coding (SC) is an unsupervised learning scheme that has received an increasing amount of interests in recent years.
Accurate Deep Representation Quantization with Gradient Snapping Layer for Similarity Search
However, how to learn deep representations that strongly preserve similarities between data pairs and can be accurately quantized via vector quantization remains a challenging task.
Multi-View Constraint Propagation with Consensus Prior Knowledge
In this paper, we present a method dubbed Consensus Prior Constraint Propagation (CPCP), which can provide the prior knowledge of the robustness of each data instance and its neighborhood.
Deep CTR Prediction in Display Advertising
Click through rate (CTR) prediction of image ads is the core task of online display advertising systems, and logistic regression (LR) has been frequently applied as the prediction model.
Adaptive Affinity Matrix for Unsupervised Metric Learning
In this paper, we propose a novel method, dubbed Adaptive Affinity Matrix (AdaAM), to learn an adaptive affinity matrix and derive a distance metric from the affinity.
Fast Non-local Stereo Matching based on Hierarchical Disparity Prediction
This is partially because our DTs overcome the extreme greediness of the MST.
HCLAE: High Capacity Locally Aggregating Encodings for Approximate Nearest Neighbor Search
Further, we propose Aggregating-Tree (A-Tree), a non-exhaustive search method using HCLAE to perform efficient ANN-Search.
Accelerated Distance Computation with Encoding Tree for High Dimensional Data
We propose a novel distance to calculate distance between high dimensional vector pairs, utilizing vector quantization generated encodings.
Improved Residual Vector Quantization for High-dimensional Approximate Nearest Neighbor Search
In this paper, we propose an improved residual vector quantization (IRVQ) method, our IRVQ learns codebook with a hybrid method of subspace clustering and warm-started k-means on each stage to prevent performance gain from dropping, and uses a multi-path encoding scheme to encode a vector with lower distortion.
Learning Better Encoding for Approximate Nearest Neighbor Search with Dictionary Annealing
Jointly used with residual vector quantization, our optimized dictionaries lead to a better approximate nearest neighbor search performance compared to the state-of-the-art methods.
