Search Results for author:
Found 53 papers, 34 papers with code
Polysemy Deciphering Network for Human-Object Interaction Detection
First, PD-Net augments human pose and spatial features for HOI detection using language priors, enabling the verb classifiers to receive language hints that reduce the intra-class variation of the same verb.
Beyond Human Data: Aligning Multimodal Large Language Models by Iterative Self-Evolution
To address these issues, we propose a novel multimodal self-evolution framework that enables the model to autonomously generate high-quality questions and answers using only unannotated images.
Simultaneous Computation and Memory Efficient Zeroth-Order Optimizer for Fine-Tuning Large Language Models
By revisiting the Memory-efficient ZO (MeZO) optimizer, we discover that the full-parameter perturbation and updating processes consume over 50% of its overall fine-tuning time cost.
Harnessing the Power of MLLMs for Transferable Text-to-Image Person ReID
Thus, we propose a novel method that uses MLLMs to caption images according to various templates.
Disentangled Pre-training for Human-Object Interaction Detection
Therefore, we propose an efficient disentangled pre-training method for HOI detection (DP-HOI) to address this problem.
Texture-Preserving Diffusion Models for High-Fidelity Virtual Try-On
Second, we propose a novel diffusion-based method that predicts a precise inpainting mask based on the person and reference garment images, further enhancing the reliability of the try-on results.
Towards Variable and Coordinated Holistic Co-Speech Motion Generation
This paper addresses the problem of generating lifelike holistic co-speech motions for 3D avatars, focusing on two key aspects: variability and coordination.
Local-consistent Transformation Learning for Rotation-invariant Point Cloud Analysis
Equipped with LCRF and RPR, our LocoTrans is capable of learning local-consistent transformation and preserving local geometry, which benefits rotation invariance learning.
Trajectory Consistency Distillation: Improved Latent Consistency Distillation by Semi-Linear Consistency Function with Trajectory Mapping
Consequently, we introduce Trajectory Consistency Distillation (TCD), which encompasses trajectory consistency function and strategic stochastic sampling.
Decoupled Prototype Learning for Reliable Test-Time Adaptation
Second, we propose a memory-based strategy to enhance DPL's robustness for the small batch sizes often encountered in TTA.
Disentangled Interaction Representation for One-Stage Human-Object Interaction Detection
In this paper, we improve the performance of one-stage methods by enabling them to extract disentangled interaction representations.
Unified Pre-training with Pseudo Texts for Text-To-Image Person Re-identification
In this way, the pre-training task and the T2I-ReID task are made consistent with each other on both data and training levels.
DARC: Distribution-Aware Re-Coloring Model for Generalizable Nucleus Segmentation
Second, we propose a new instance normalization method that is robust to the variation in foreground-background ratios.
Can Linguistic Knowledge Improve Multimodal Alignment in Vision-Language Pretraining?
The multimedia community has shown a significant interest in perceiving and representing the physical world with multimodal pretrained neural network models, and among them, the visual-language pertaining (VLP) is, currently, the most captivating topic.
Cross-modal & Cross-domain Learning for Unsupervised LiDAR Semantic Segmentation
In recent years, cross-modal domain adaptation has been studied on the paired 2D image and 3D LiDAR data to ease the labeling costs for 3D LiDAR semantic segmentation (3DLSS) in the target domain.
MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
To this end, we propose to generate images conditioned on the compositions of multimodal control signals, where modalities are imperfectly complementary, i. e., composed multimodal conditional image synthesis (CMCIS).
Mining False Positive Examples for Text-Based Person Re-identification
Text-based person re-identification (ReID) aims to identify images of the targeted person from a large-scale person image database according to a given textual description.
HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization
Recovery of an underlying scene geometry from multiview images stands as a long-time challenge in computer vision research.
Harmonious Feature Learning for Interactive Hand-Object Pose Estimation
Notably, the performance of our model on hand pose estimation even surpasses that of existing works that only perform the single-hand pose estimation task.
Ranked #2 on
hand-object pose
on DexYCB
Learning Granularity-Unified Representations for Text-to-Image Person Re-identification
In PGU, we adopt a set of shared and learnable prototypes as the queries to extract diverse and semantically aligned features for both modalities in the granularity-unified feature space, which further promotes the ReID performance.
Category-Level 6D Object Pose and Size Estimation using Self-Supervised Deep Prior Deformation Networks
It is difficult to precisely annotate object instances and their semantics in 3D space, and as such, synthetic data are extensively used for these tasks, e. g., category-level 6D object pose and size estimation.
Towards Hard-Positive Query Mining for DETR-based Human-Object Interaction Detection
Specifically, we shift the GT bounding boxes of each labeled human-object pair so that the shifted boxes cover only a certain portion of the GT ones.
1st Place Solution to the EPIC-Kitchens Action Anticipation Challenge 2022
In this report, we describe the technical details of our submission to the EPIC-Kitchens Action Anticipation Challenge 2022.
Style Interleaved Learning for Generalizable Person Re-identification
This common practice causes the model to overfit to existing feature styles in the source domain, resulting in sub-optimal generalization ability on target domains.
Context Sensing Attention Network for Video-based Person Re-identification
In this work, we propose a novel Context Sensing Attention Network (CSA-Net), which improves both the frame feature extraction and temporal aggregation steps.
HL-Net: Heterophily Learning Network for Scene Graph Generation
Despite their effectiveness, however, current SGG methods only assume scene graph homophily while ignoring heterophily.
Few-Shot Head Swapping in the Wild
Particularly, seamless blending is achieved with the help of a Semantic-Guided Color Reference Creation procedure and a Blending UNet.
MobileFaceSwap: A Lightweight Framework for Video Face Swapping
In this work, we propose a lightweight Identity-aware Dynamic Network (IDN) for subject-agnostic face swapping by dynamically adjusting the model parameters according to the identity information.
Distillation Using Oracle Queries for Transformer-Based Human-Object Interaction Detection
Our methods significantly promote both the accuracy and training efficiency of transformer-based HOI detection models.
Quality-aware Part Models for Occluded Person Re-identification
Existing approaches typically rely on outside tools to infer visible body parts, which may be suboptimal in terms of both computational efficiency and ReID accuracy.
Uncertainty-aware Clustering for Unsupervised Domain Adaptive Object Re-identification
In particular, the performance of our unsupervised UCF method in the MSMT17$\to$Market1501 task is better than that of the fully supervised setting on Market1501.
Semantically Self-Aligned Network for Text-to-Image Part-aware Person Re-identification
Third, we introduce a Compound Ranking (CR) loss that makes use of textual descriptions for other images of the same identity to provide extra supervision, thereby effectively reducing the intra-class variance in textual features.
Ranked #1 on
Image Retrieval
on ICFG-PEDES
Attention-guided Progressive Mapping for Profile Face Recognition
Firstly, to reduce the difficulty of directly transforming the profile face features into a frontal pose, we propose to learn the feature residual between the source pose and its nearby pose in a block-byblock fashion, and thus traversing to the feature space of a smaller pose by adding the learned residual.
Glance and Gaze: Inferring Action-aware Points for One-Stage Human-Object Interaction Detection
In this paper, we propose a novel one-stage method, namely Glance and Gaze Network (GGNet), which adaptively models a set of actionaware points (ActPoints) via glance and gaze steps.
Ranked #17 on
Human-Object Interaction Detection
on V-COCO
On Universal Black-Box Domain Adaptation
The great promise that UB$^2$DA makes, however, brings significant learning challenges, since domain adaptation can only rely on the predictions of unlabeled target data in a partially overlapped label space, by accessing the interface of source model.
CPP-Net: Context-aware Polygon Proposal Network for Nucleus Segmentation
Each polygon is represented by a set of centroid-to-boundary distances, which are in turn predicted by features of the centroid pixel for a single nucleus.
Classification of Single-View Object Point Clouds
By adapting existing ModelNet40 and ScanNet datasets to the single-view, partial setting, experiment results can verify the necessity of object pose estimation and superiority of our PAPNet to existing classifiers.
Batch Coherence-Driven Network for Part-aware Person Re-Identification
First, we introduce a batch coherence-guided channel attention (BCCA) module that highlights the relevant channels for each respective part from the output of a deep backbone model.
Polysemy Deciphering Network for Robust Human-Object Interaction Detection
To address this issue, in this paper, we propose a novel Polysemy Deciphering Network (PD-Net) that decodes the visual polysemy of verbs for HOI detection in three distinct ways.
Ranked #19 on
Human-Object Interaction Detection
on V-COCO
Boundary-assisted Region Proposal Networks for Nucleus Segmentation
Accordingly, in this paper, we devise a Boundary-assisted Region Proposal Network (BRP-Net) that achieves robust instance-level nucleus segmentation.
Learning Oracle Attention for High-fidelity Face Completion
While recent works adopted the attention mechanism to learn the contextual relations among elements of the face, they have largely overlooked the disastrous impacts of inaccurate attention scores; in addition, they fail to pay sufficient attention to key facial components, the completion results of which largely determine the authenticity of a face image.
GPS-Net: Graph Property Sensing Network for Scene Graph Generation
There are three key properties of scene graph that have been underexplored in recent works: namely, the edge direction information, the difference in priority between nodes, and the long-tailed distribution of relationships.
Ranked #5 on
Scene Graph Generation
on Visual Genome
Multi-task Learning with Coarse Priors for Robust Part-aware Person Re-identification
MPN has three key advantages: 1) it does not need to conduct body part detection in the inference stage; 2) its model is very compact and efficient for both training and testing; 3) in the training stage, it requires only coarse priors of body part locations, which are easy to obtain.
Ranked #5 on
Person Re-Identification
on CUHK03 detected
CDPM: Convolutional Deformable Part Models for Semantically Aligned Person Re-identification
Part-level representations are essential for robust person re-identification.
Soft-ranking Label Encoding for Robust Facial Age Estimation
Moreover, we also carefully analyze existing evaluation protocols for age estimation, finding that the overlap in identity between the training and testing sets affects the relative performance of different age encoding methods.
One-pass Multi-task Networks with Cross-task Guided Attention for Brain Tumor Segmentation
The model cascade (MC) strategy significantly alleviates the class imbalance issue via running a set of individual deep models for coarse-to-fine segmentation.
Ranked #1 on
Brain Tumor Segmentation
on BRATS-2015
(using extra training data)
Identifying the Best Machine Learning Algorithms for Brain Tumor Segmentation, Progression Assessment, and Overall Survival Prediction in the BRATS Challenge
This study assesses the state-of-the-art machine learning (ML) methods used for brain tumor image analysis in mpMRI scans, during the last seven instances of the International Brain Tumor Segmentation (BraTS) challenge, i. e., 2012-2018.
Correcting the Triplet Selection Bias for Triplet Loss
Considering that the number of triplets grows cubically with the size of training data, triplet mining is thus indispensable for efficiently training with triplet loss.
Trunk-Branch Ensemble Convolutional Neural Networks for Video-based Face Recognition
Second, to enhance robustness of CNN features to pose variations and occlusion, we propose a Trunk-Branch Ensemble CNN model (TBE-CNN), which extracts complementary information from holistic face images and patches cropped around facial components.
Robust Face Recognition via Multimodal Deep Face Representation
The proposed deep learning structure is composed of a set of elaborately designed convolutional neural networks (CNNs) and a three-layer stacked auto-encoder (SAE).
A Comprehensive Survey on Pose-Invariant Face Recognition
The capacity to recognize faces under varied poses is a fundamental human ability that presents a unique challenge for computer vision systems.
Multi-Directional Multi-Level Dual-Cross Patterns for Robust Face Recognition
To perform unconstrained face recognition robust to variations in illumination, pose and expression, this paper presents a new scheme to extract "Multi-Directional Multi-Level Dual-Cross Patterns" (MDML-DCPs) from face images.
