Search Results for author:
Found 71 papers, 23 papers with code
Map Optical Properties to Subwavelength Structures Directly via a Diffusion Model
The inverse design methods proposed for these subwavelength structures are vital to the development of new photonic devices.
OV-Uni3DETR: Towards Unified Open-Vocabulary 3D Object Detection via Cycle-Modality Propagation
Specifically, we propose the cycle-modality propagation, aimed at propagating knowledge bridging 2D and 3D modalities, to support the aforementioned functionalities.
Joint Learning for Scattered Point Cloud Understanding with Hierarchical Self-Distillation
Numerous point-cloud understanding techniques focus on whole entities and have succeeded in obtaining satisfactory results and limited sparsity tolerance.
Uni3DETR: Unified 3D Detection Transformer
In this paper, we propose Uni3DETR, a unified 3D detector that addresses indoor and outdoor 3D detection within the same framework.
Alice Benchmarks: Connecting Real World Re-Identification with the Synthetic
In this paper, we detail the settings of Alice benchmarks, provide an analysis of existing commonly-used domain adaptation methods, and discuss some interesting future directions.
Identity-Seeking Self-Supervised Representation Learning for Generalizable Person Re-identification
To overcome the barriers of data and annotation, we propose to utilize large-scale unsupervised data for training.
Generalizable Person Re-identification
Representation Learning
Learning Prompt-Enhanced Context Features for Weakly-Supervised Video Anomaly Detection
Additionally, we propose a Prompt-Enhanced Learning (PEL) module that integrates semantic priors using knowledge-based prompts to boost the discriminative capacity of context features while ensuring separability between anomaly sub-classes.
Anomaly Detection In Surveillance Videos
Video Anomaly Detection
+1
Detecting Everything in the Open World: Towards Universal Object Detection
In this paper, we formally address universal object detection, which aims to detect every scene and predict every category.
Generalizable Re-Identification from Videos with Cycle Association
In this paper, we are interested in learning a generalizable person re-identification (re-ID) representation from unlabeled videos.
Domain Generalization
Generalizable Person Re-identification
+1
Reliability-Aware Prediction via Uncertainty Learning for Person Image Retrieval
(3) the data uncertainty and the model uncertainty are jointly learned in a unified network, and they serve as two fundamental criteria for the reliability assessment: if a probe is high-quality (low data uncertainty) and the model is confident in the prediction of the probe (low model uncertainty), the final ranking will be assessed as reliable.
Self-Supervised Learning via Maximum Entropy Coding
To cope with this issue, we propose Maximum Entropy Coding (MEC), a more principled objective that explicitly optimizes on the structure of the representation, so that the learned representation is less biased and thus generalizes better to unseen downstream tasks.
GraphCSPN: Geometry-Aware Depth Completion via Dynamic GCNs
First, unlike previous methods, we leverage convolution neural networks as well as graph neural networks in a complementary way for geometric representation learning.
Portrait Interpretation and a Benchmark
Furthermore, we focus on representation learning for portrait interpretation and propose a baseline that reflects our systematic perspective.
Hybrid Physical Metric For 6-DoF Grasp Pose Detection
6-DoF grasp pose detection of multi-grasp and multi-object is a challenge task in the field of intelligent robot.
R(Det)^2: Randomized Decision Routing for Object Detection
In this paper, we propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection.
Noisy Boundaries: Lemon or Lemonade for Semi-supervised Instance Segmentation?
We construct a framework for semi-supervised instance segmentation by assigning pixel-level pseudo labels.
OSKDet: Orientation-Sensitive Keypoint Localization for Rotated Object Detection
By proposing the orientation-sensitive heatmap, OSKDet could learn the shape and direction of rotated target implicitly and has stronger modeling capabilities for rotated representation, which improves the localization accuracy and acquires high quality detection results.
R(Det)2: Randomized Decision Routing for Object Detection
In this paper, we propose a novel approach to combine decision trees and deep neural networks in an end-to-end learning manner for object detection.
Delving into Probabilistic Uncertainty for Unsupervised Domain Adaptive Person Re-Identification
With the uncertainty-guided alternative optimization, we balance between the exploration of target domain data and the negative effects of noisy labeling.
Adaptive Affinity for Associations in Multi-Target Multi-Camera Tracking
In this paper, we design experiments to verify such misfit between global re-ID feature distances and local matching in tracking, and propose a simple yet effective approach to adapt affinity estimations to corresponding matching scopes in MTMCT.
Combating Noise: Semi-supervised Learning by Region Uncertainty Quantification
To combat the noisy labeling, we propose noise-resistant semi-supervised learning by quantifying the region uncertainty.
EFENet: Reference-based Video Super-Resolution with Enhanced Flow Estimation
In this paper, we consider the problem of reference-based video super-resolution(RefVSR), i. e., how to utilize a high-resolution (HR) reference frame to super-resolve a low-resolution (LR) video sequence.
Reference-based Video Super-Resolution
Video Super-Resolution
Towards Discriminative Representation Learning for Unsupervised Person Re-identification
We observe that these proposed schemes are capable of facilitating the learning of discriminative feature representations.
Do Different Tracking Tasks Require Different Appearance Models?
We show how most tracking tasks can be solved within this framework, and that the same appearance model can be successfully used to obtain results that are competitive against specialised methods for most of the tasks considered.
Ranked #2 on
Video Object Segmentation
on DAVIS 2017
(mIoU metric)
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+10
A2-FPN: Attention Aggregation Based Feature Pyramid Network for Instance Segmentation
Learning pyramidal feature representations is crucial for recognizing object instances at different scales.
AdaZoom: Adaptive Zoom Network for Multi-Scale Object Detection in Large Scenes
In this paper, we propose a novel Adaptive Zoom (AdaZoom) network as a selective magnifier with flexible shape and focal length to adaptively zoom the focus regions for object detection.
Multi-Target Domain Adaptation with Collaborative Consistency Learning
To obtain a single model that works across multiple target domains, we propose to simultaneously learn a student model which is trained to not only imitate the output of each expert on the corresponding target domain, but also to pull different expert close to each other with regularization on their weights.
Ranked #4 on
Domain Adaptation
on GTAV to Cityscapes+Mapillary
A^2-FPN: Attention Aggregation based Feature Pyramid Network for Instance Segmentation
Learning pyramidal feature representations is crucial for recognizing object instances at different scales.
Data-Uncertainty Guided Multi-Phase Learning for Semi-Supervised Object Detection
In this paper, we delve into semi-supervised object detection where unlabeled images are leveraged to break through the upper bound of fully-supervised object detection models.
Partial Off-Policy Learning: Balance Accuracy and Diversity for Human-Oriented Image Captioning
Human-oriented image captioning with both high diversity and accuracy is a challenging task in vision+language modeling.
Disentangled Representation for Age-Invariant Face Recognition: A Mutual Information Minimization Perspective
For quantitative measure of the degree of disentanglement, we verify that mutual information can represent as metric.
Revisiting Temporal Modeling for Video Super-resolution
Video super-resolution plays an important role in surveillance video analysis and ultra-high-definition video display, which has drawn much attention in both the research and industrial communities.
Ranked #1 on
Video Super-Resolution
on SPMCS - 4x upscaling
Video Super-Resolution with Recurrent Structure-Detail Network
Most video super-resolution methods super-resolve a single reference frame with the help of neighboring frames in a temporal sliding window.
Video Super-resolution with Temporal Group Attention
Video super-resolution, which aims at producing a high-resolution video from its corresponding low-resolution version, has recently drawn increasing attention.
CycAs: Self-supervised Cycle Association for Learning Re-identifiable Descriptions
This paper proposes a self-supervised learning method for the person re-identification (re-ID) problem, where existing unsupervised methods usually rely on pseudo labels, such as those from video tracklets or clustering.
Locality Aware Appearance Metric for Multi-Target Multi-Camera Tracking
Due to the continuity of target trajectories, tracking systems usually restrict their data association within a local neighborhood.
Applying BERT to Document Retrieval with Birch
We present Birch, a system that applies BERT to document retrieval via integration with the open-source Anserini information retrieval toolkit to demonstrate end-to-end search over large document collections.
Towards Real-Time Multi-Object Tracking
In this paper, we propose an MOT system that allows target detection and appearance embedding to be learned in a shared model.
Ranked #4 on
Multi-Object Tracking
on HiEve
Adversarial View-Consistent Learning for Monocular Depth Estimation
To this end, we first design a differentiable depth map warping operation, which is end-to-end trainable, and then propose a pose generator to generate novel views for a given image in an adversarial manner.
Softmax Dissection: Towards Understanding Intra- and Inter-class Objective for Embedding Learning
The softmax loss and its variants are widely used as objectives for embedding learning, especially in applications like face recognition.
CS-R-FCN: Cross-supervised Learning for Large-Scale Object Detection
Generic object detection is one of the most fundamental problems in computer vision, yet it is difficult to provide all the bounding-box-level annotations aiming at large-scale object detection for thousands of categories.
Intra-clip Aggregation for Video Person Re-identification
Video-based person re-identification has drawn massive attention in recent years due to its extensive applications in video surveillance.
HAR-Net: Joint Learning of Hybrid Attention for Single-stage Object Detection
First, we present the modules of spatial attention, channel attention and aligned attention for single-stage object detection.
Perceive Where to Focus: Learning Visibility-aware Part-level Features for Partial Person Re-identification
The visibility awareness allows VPM to extract region-level features and compare two images with focus on their shared regions (which are visible on both images).
Ranked #14 on
Person Re-Identification
on Market-1501-C
Linkage Based Face Clustering via Graph Convolution Network
The key idea is that we find the local context in the feature space around an instance (face) contains rich information about the linkage relationship between this instance and its neighbors.
Intention Oriented Image Captions with Guiding Objects
In this paper, we propose a novel approach for generating image captions with guiding objects (CGO).
Query Adaptive Late Fusion for Image Retrieval
That is to say, for some queries, a feature may be neither discriminative nor complementary to existing ones, while for other queries, the feature suffices.
DeepDeblur: Fast one-step blurry face images restoration
Comprehensive experiments demonstrate that our proposed method can handle various blur kenels and achieve state-of-the-art results for small size blurry face images restoration.
Beyond Part Models: Person Retrieval with Refined Part Pooling (and a Strong Convolutional Baseline)
RPP re-assigns these outliers to the parts they are closest to, resulting in refined parts with enhanced within-part consistency.
Ranked #3 on
Person Re-Identification
on UAV-Human
Progressive Representation Adaptation for Weakly Supervised Object Localization
In classification adaptation, we transfer a pre-trained network to a multi-label classification task for recognizing the presence of a certain object in an image.
Orientation Invariant Feature Embedding and Spatial Temporal Regularization for Vehicle Re-Identification
In our vehicle ReID framework, an orientation invariant feature embedding module and a spatial-temporal regularization module are proposed.
SegFlow: Joint Learning for Video Object Segmentation and Optical Flow
This paper proposes an end-to-end trainable network, SegFlow, for simultaneously predicting pixel-wise object segmentation and optical flow in videos.
Ranked #67 on
Semi-Supervised Video Object Segmentation
on DAVIS 2016
Learning to Segment Instances in Videos with Spatial Propagation Network
In addition, we apply a filter on the refined score map that aims to recognize the best connected region using spatial and temporal consistencies in the video.
Learning Structured Semantic Embeddings for Visual Recognition
First, we exploit the discriminative constraints to capture the intra- and inter-class relationships of image embeddings.
Metric Learning in Codebook Generation of Bag-of-Words for Person Re-identification
Person re-identification is generally divided into two part: first how to represent a pedestrian by discriminative visual descriptors and second how to compare them by suitable distance metrics.
SVDNet for Pedestrian Retrieval
This paper proposes the SVDNet for retrieval problems, with focus on the application of person re-identification (re-ID).
Ranked #14 on
Person Re-Identification
on CUHK03 detected
Weakly Supervised Object Localization With Progressive Domain Adaptation
In this paper, we address this problem by progressive domain adaptation with two main steps: classification adaptation and detection adaptation.
Good Practice in CNN Feature Transfer
The objective of this paper is the effective transfer of the Convolutional Neural Network (CNN) feature in image search and classification.
Person Re-Identification by Discriminative Selection in Video Ranking
Current person re-identification (ReID) methods typically rely on single-frame imagery features, whilst ignoring space-time information from image sequences often available in the practical surveillance scenarios.
Scalable Person Re-Identification: A Benchmark
As a minor contribution, inspired by recent advances in large-scale image search, this paper proposes an unsupervised Bag-of-Words descriptor.
Ranked #90 on
Person Re-Identification
on DukeMTMC-reID
Fast Orthogonal Projection Based on Kronecker Product
We propose a family of structured matrices to speed up orthogonal projections for high-dimensional data commonly seen in computer vision applications.
Query-Adaptive Late Fusion for Image Search and Person Re-Identification
However, in a more realistic situation, one does not know in advance whether a feature is effective or not for a given query.
Deep Transfer Network: Unsupervised Domain Adaptation
In this paper, we propose a new domain adaptation framework named Deep Transfer Network (DTN), where the highly flexible deep neural networks are used to implement such a distribution matching process.
Person Re-identification Meets Image Search
In the light of recent advances in image search, this paper proposes to treat person re-identification as an image search problem.
Beyond $χ^2$ Difference: Learning Optimal Metric for Boundary Detection
To improve the performance of boundary detection, a Learning-based Boundary Metric (LBM) is proposed to replace $\chi^2$ difference adopted by the classical algorithm mPb.
Visual Reranking with Improved Image Graph
This paper introduces an improved reranking method for the Bag-of-Words (BoW) based image search.
Seeing the Big Picture: Deep Embedding with Contextual Evidences
Specifically, the Convolutional Neural Network (CNN) is employed to extract features from regional and global patches, leading to the so-called "Deep Embedding" framework.
Bayes Merging of Multiple Vocabularies for Scalable Image Retrieval
Albeit simple, Bayes merging can be well applied in various merging tasks, and consistently improves the baselines on multi-vocabulary merging.
Packing and Padding: Coupled Multi-index for Accurate Image Retrieval
Specifically, we exploit the fusion of local color feature into c-MI.
Lp-Norm IDF for Large Scale Image Search
Further, by counting for the term-frequency in each image, the proposed L p -norm IDF helps to alleviate the visual word burstiness phenomenon.
