Search Results for author:
Found 41 papers, 12 papers with code
Enhancing Semantic Consistency of Large Language Models through Model Editing: An Interpretability-Oriented Approach
In this paper, we are motivated to enhance the semantic consistency of LLMs through a more interpretable method (i. e., model editing) to this end.
A Survey on Hallucination in Large Vision-Language Models
In this comprehensive survey, we dissect LVLM-related hallucinations in an attempt to establish an overview and facilitate future mitigation.
Align before Adapt: Leveraging Entity-to-Region Alignments for Generalizable Video Action Recognition
With the aligned entities, we feed their text embeddings to a transformer-based video adapter as the queries, which can help extract the semantics of the most important entities from a video to a vector.
PBFormer: Capturing Complex Scene Text Shape with Polynomial Band Transformer
We present PBFormer, an efficient yet powerful scene text detector that unifies the transformer with a novel text shape representation Polynomial Band (PB).
ChartDETR: A Multi-shape Detection Network for Visual Chart Recognition
Visual chart recognition systems are gaining increasing attention due to the growing demand for automatically identifying table headers and values from chart images.
Video Action Recognition with Attentive Semantic Units
Supervised by the semantics of action labels, recent works adapt the visual branch of VLMs to learn video representations.
Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling
The ablation study also validates that the proposed coordinate sequence decoder and the visual-alignment loss are the keys to the success of our method.
FNeVR: Neural Volume Rendering for Face Animation
In FNeVR, we design a 3D Face Volume Rendering (FVR) module to enhance the facial details for image rendering.
Pseudo-Pair based Self-Similarity Learning for Unsupervised Person Re-identification
In this paper, we present a pseudo-pair based self-similarity learning approach for unsupervised person re-ID without human annotations.
Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints
In this task, the correct camera pose is the key to generating accurate lanes, which can transform an image from perspective-view to the top-view.
Ranked #7 on
3D Lane Detection
on Apollo Synthetic 3D Lane
Mutual CRF-GNN for Few-Shot Learning
In this MCGN, the labels and features of support data are used by the CRF for inferring GNN affinities in a principled and probabilistic way.
Multiple Domain Experts Collaborative Learning: Multi-Source Domain Generalization For Person Re-Identification
In UDCL, a universal expert supervises the learning of domain experts and continuously gathers knowledge from all domain experts.
Layerwise Optimization by Gradient Decomposition for Continual Learning
The gradient for update should be close to the gradient of the new task, consistent with the gradients shared by all old tasks, and orthogonal to the space spanned by the gradients specific to the old tasks.
Neighbourhood-guided Feature Reconstruction for Occluded Person Re-Identification
Person images captured by surveillance cameras are often occluded by various obstacles, which lead to defective feature representation and harm person re-identification (Re-ID) performance.
Complementary Relation Contrastive Distillation
Specifically, we estimate the mutual relation in an anchor-based way and distill the anchor-student relation under the supervision of its corresponding anchor-teacher relation.
Ranked #37 on
Knowledge Distillation
on ImageNet
Gradient Regularized Contrastive Learning for Continual Domain Adaptation
To better understand this issue, we study the problem of continual domain adaptation, where the model is presented with a labelled source domain and a sequence of unlabelled target domains.
Online Pseudo Label Generation by Hierarchical Cluster Dynamics for Adaptive Person Re-Identification
To tackle the problem, we propose an online pseudo label generation by hierarchical cluster dynamics for adaptive ReID.
Differentiable Dynamic Wirings for Neural Networks
A standard practice of deploying deep neural networks is to apply the same architecture to all the input instances.
Dynamic Graph: Learning Instance-aware Connectivity for Neural Networks
To facilitate the training, we represent the network connectivity of each sample in an adjacency matrix.
Improved Mutual Mean-Teaching for Unsupervised Domain Adaptive Re-ID
SDA, a domain-translation-based framework, focuses on carefully translating the source-domain images to the target domain.
Continual Representation Learning for Biometric Identification
With the explosion of digital data in recent years, continuously learning new tasks from a stream of data without forgetting previously acquired knowledge has become increasingly important.
Self-paced Contrastive Learning with Hybrid Memory for Domain Adaptive Object Re-ID
To solve these problems, we propose a novel self-paced contrastive learning framework with hybrid memory.
Ranked #4 on
Unsupervised Domain Adaptation
on Market to MSMT
COCAS: A Large-Scale Clothes Changing Person Dataset for Re-identification
To address the clothes changing person re-id problem, we construct a novel large-scale re-id benchmark named ClOthes ChAnging Person Set (COCAS), which provides multiple images of the same identity with different clothes.
Learning to Cluster Faces via Confidence and Connectivity Estimation
With the vertex confidence and edge connectivity, we can naturally organize more relevant vertices on the affinity graph and group them into clusters.
Adapting Object Detectors with Conditional Domain Normalization
Then this domain-vector is used to encode the features from another domain through a conditional normalization, resulting in different domains' features carrying the same domain attribute.
Ranked #1 on
Unsupervised Domain Adaptation
on SIM10K to BDD100K
Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term.
Ranked #5 on
Unsupervised Domain Adaptation
on Market to MSMT
Mutual Mean-Teaching: Pseudo Label Refinery for Unsupervised Domain Adaptation on Person Re-identification
In order to mitigate the effects of noisy pseudo labels, we propose to softly refine the pseudo labels in the target domain by proposing an unsupervised framework, Mutual Mean-Teaching (MMT), to learn better features from the target domain via off-line refined hard pseudo labels and on-line refined soft pseudo labels in an alternative training manner.
Ranked #1 on
Unsupervised Person Re-Identification
on DukeMTMC-reID->Market-1501
(Top-1 (%) metric)
Memory-Based Neighbourhood Embedding for Visual Recognition
Learning discriminative image feature embeddings is of great importance to visual recognition.
Learning to Cluster Faces on an Affinity Graph
Face recognition sees remarkable progress in recent years, and its performance has reached a very high level.
Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
Person re-identification is an important task that requires learning discriminative visual features for distinguishing different person identities.
Ranked #24 on
Text based Person Retrieval
on CUHK-PEDES
Deep Group-shuffling Random Walk for Person Re-identification
Person re-identification aims at finding a person of interest in an image gallery by comparing the probe image of this person with all the gallery images.
Person Re-identification with Deep Similarity-Guided Graph Neural Network
However, existing person re-identification models mostly estimate the similarities of different image pairs of probe and gallery images independently while ignores the relationship information between different probe-gallery pairs.
Ranked #1 on
Person Re-Identification
on CUHK03
Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet Embedding
The attention weights are obtained based on a query feature, which is learned from the whole probe snippet by an LSTM network, making the resulting embeddings less affected by noisy frames.
Ranked #4 on
Person Re-Identification
on PRID2011
Group Consistent Similarity Learning via Deep CRF for Person Re-Identification
Extensive experiments demonstrate the effectiveness of our model that combines DNN and CRF for learning robust multi-scale local similarities.
Show, Tell and Discriminate: Image Captioning by Self-retrieval with Partially Labeled Data
The aim of image captioning is to generate captions by machine to describe image contents.
Long-term Multi-granularity Deep Framework for Driver Drowsiness Detection
For real-world driver drowsiness detection from videos, the variation of head pose is so large that the existing methods on global face is not capable of extracting effective features, such as looking aside and lowering head.
Learning Fixation Point Strategy for Object Detection and Classification
The network can learn to extract a sequence of local observations with detailed appearance and rough context, instead of sliding windows or convolutions on the entire image.
Weighted Motion Averaging for the Registration of Multi-View Range Scans
With the overlapping percentage available, it views the overlapping percentage as the corresponding weight of each scan pair and proposes the weight motion averaging algorithm, which can pay more attention to reliable and accurate relative motions.
Coordinating Multiple Disparity Proposals for Stereo Computation
While great progress has been made in stereo computation over the last decades, large textureless regions remain challenging.
Similarity Learning With Spatial Constraints for Person Re-Identification
We therefore learn a novel similarity function, which consists of multiple sub-similarity measurements with each taking in charge of a subregion.
Similarity Learning on an Explicit Polynomial Kernel Feature Map for Person Re-Identification
We follow the learning-to-rank methodology and learn a similarity function to maximize the difference between the similarity scores of matched and unmatched images for a same person.
