Search Results for author:
Found 67 papers, 23 papers with code
Count- and Similarity-aware R-CNN for Pedestrian Detection
We further introduce a count-and-similarity branch within the two-stage detection framework, which predicts pedestrian count as well as proposal similarity.
CLIPer: Hierarchically Improving Spatial Representation of CLIP for Open-Vocabulary Semantic Segmentation
The proposed CLIPer includes an early-layer fusion module and a fine-grained compensation module.
Open Vocabulary Semantic Segmentation
Open-Vocabulary Semantic Segmentation
+2
Multi-Stage Knowledge Integration of Vision-Language Models for Continual Learning
One is the popularly adopted single-teacher paradigm fails to impart comprehensive knowledge, The other is the existing methods inadequately leverage the multimodal information in the original training dataset, instead they rely on additional data for distillation, which increases computational and storage overhead.
A Fresh Look at Generalized Category Discovery through Non-negative Matrix Factorization
Generalized Category Discovery (GCD) aims to classify both base and novel images using labeled base data.
iSeg: An Iterative Refinement-based Framework for Training-free Segmentation
Leveraging the entropy-reduced self-attention module, our iSeg stably improves refined cross-attention map with iterative refinement.
Parameter-Efficient Fine-Tuning for Continual Learning: A Neural Tangent Kernel Perspective
This work provides a theoretical foundation for understanding and improving PEFT-CL models, offering insights into the interplay between feature representation, task orthogonality, and generalization, contributing to the development of more efficient continual learning systems.
Raformer: Redundancy-Aware Transformer for Video Wire Inpainting
Video Wire Inpainting (VWI) is a prominent application in video inpainting, aimed at flawlessly removing wires in films or TV series, offering significant time and labor savings compared to manual frame-by-frame removal.
VFMM3D: Releasing the Potential of Image by Vision Foundation Model for Monocular 3D Object Detection
Therefore, an effective solution involves transforming monocular images into LiDAR-like representations and employing a LiDAR-based 3D object detector to predict the 3D coordinates of objects.
Implicit and Explicit Language Guidance for Diffusion-based Visual Perception
The explicit branch utilizes the ground-truth labels of corresponding images as text prompts to condition feature extraction of diffusion model.
The state-of-the-art in Cardiac MRI Reconstruction: Results of the CMRxRecon Challenge in MICCAI 2023
To address this issue, we organized the Cardiac MRI Reconstruction Challenge (CMRxRecon) in 2023, in collaboration with the 26th International Conference on MICCAI.
NTK-Guided Few-Shot Class Incremental Learning
Through the combined effects of these measures, our network acquires robust NTK properties, ensuring optimal convergence and stability of the NTK matrix and minimizing the NTK-related generalization loss, significantly enhancing its theoretical generalization.
class-incremental learning
Few-Shot Class-Incremental Learning
+2
CLIP-VIS: Adapting CLIP for Open-Vocabulary Video Instance Segmentation
The experiments are performed on various video instance segmentation datasets, which demonstrate the effectiveness of our proposed method, especially for novel categories.
Joint Attention-Guided Feature Fusion Network for Saliency Detection of Surface Defects
To address these issues, we propose a joint attention-guided feature fusion network (JAFFNet) for saliency detection of surface defects based on the encoder-decoder network.
SED: A Simple Encoder-Decoder for Open-Vocabulary Semantic Segmentation
In this paper, we propose a simple encoder-decoder, named SED, for open-vocabulary semantic segmentation, which comprises a hierarchical encoder-based cost map generation and a gradual fusion decoder with category early rejection.
Hierarchical Matching and Reasoning for Multi-Query Image Retrieval
Afterwards, the VR module is developed to excavate the potential semantic correlations among multiple region-query pairs, which further explores the high-level reasoning similarity.
Image Reconstruction for Accelerated MR Scan with Faster Fourier Convolutional Neural Networks
To address this problem, we propose the following: (1) a novel convolutional operator called Faster Fourier Convolution (FasterFC) to replace the two consecutive convolution operations typically used in convolutional neural networks (e. g., U-Net, ResNet).
Transformer-based stereo-aware 3D object detection from binocular images
In this paper, we explore the model design of Transformers in binocular 3D object detection, focusing particularly on extracting and encoding task-specific image correspondence information.
LEAPS: End-to-End One-Step Person Search With Learnable Proposals
Given a set of sparse and learnable proposals, LEAPS employs a dynamic person search head to directly perform person detection and corresponding re-id feature generation without non-maximum suppression post-processing.
Deep Intra-Image Contrastive Learning for Weakly Supervised One-Step Person Search
We hope that our simple intra-image contrastive learning can provide more paradigms on weakly supervised person search.
USER: Unified Semantic Enhancement with Momentum Contrast for Image-Text Retrieval
(2) It limits the scale of negative sample pairs by employing the mini-batch based end-to-end training mechanism.
Memorizing Complementation Network for Few-Shot Class-Incremental Learning
Few-shot Class-Incremental Learning (FSCIL) aims at learning new concepts continually with only a few samples, which is prone to suffer the catastrophic forgetting and overfitting problems.
class-incremental learning
Few-Shot Class-Incremental Learning
+3
Multi-scale Feature Aggregation for Crowd Counting
The SkipAgg module directly propagates features with small receptive fields to features with much larger receptive fields.
PSTR: End-to-End One-Step Person Search With Transformers
We propose a novel one-step transformer-based person search framework, PSTR, that jointly performs person detection and re-identification (re-id) in a single architecture.
Dual-Domain Reconstruction Networks with V-Net and K-Net for fast MRI
Purpose: To introduce a dual-domain reconstruction network with V-Net and K-Net for accurate MR image reconstruction from undersampled k-space data.
Active Phase-Encode Selection for Slice-Specific Fast MR Scanning Using a Transformer-Based Deep Reinforcement Learning Framework
This paper aims to reducing the scan time by actively and sequentially selecting partial phases in a short time so that a slice can be accurately reconstructed from the resultant slice-specific incomplete K-space matrix.
ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection
The key in our ESGN is an efficient geometry-aware feature generation (EGFG) module.
Self-Taught Cross-Domain Few-Shot Learning with Weakly Supervised Object Localization and Task-Decomposition
However, the target domain is absolutely unknown during the training on the source domain, which results in lacking directed guidance for target tasks.
cross-domain few-shot learning
Weakly-Supervised Object Localization
Information Symmetry Matters: A Modal-Alternating Propagation Network for Few-Shot Learning
Semantic information provides intra-class consistency and inter-class discriminability beyond visual concepts, which has been employed in Few-Shot Learning (FSL) to achieve further gains.
Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection
Compared with the baseline RTS3D, our proposed method has 2. 57% improvement on AP3d almost without extra network parameters.
TJU-DHD: A Diverse High-Resolution Dataset for Object Detection
In addition, a new diverse pedestrian dataset is further built.
From Handcrafted to Deep Features for Pedestrian Detection: A Survey
In addition to single-spectral pedestrian detection, we also review multi-spectral pedestrian detection, which provides more robust features for illumination variance.
SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentation
In terms of real-time capabilities, SipMask outperforms YOLACT with an absolute gain of 3. 0% (mask AP) under similar settings, while operating at comparable speed on a Titan Xp.
Ranked #11 on
Real-time Instance Segmentation
on MSCOCO
Consensus-Aware Visual-Semantic Embedding for Image-Text Matching
In this paper, we propose a Consensus-aware Visual-Semantic Embedding (CVSE) model to incorporate the consensus information, namely the commonsense knowledge shared between both modalities, into image-text matching.
BidNet: Binocular Image Dehazing Without Explicit Disparity Estimation
On the assumption that dehazed binocular images are superior to the hazy ones for stereo vision tasks such as 3D object detection and according to the fact that image haze is a function of depth, this paper proposes a Binocular image dehazing Network (BidNet) aiming at dehazing both the left and right images of binocular images within the deep learning framework.
Hierarchical Human Parsing with Typed Part-Relation Reasoning
As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this task.
PSC-Net: Learning Part Spatial Co-occurrence for Occluded Pedestrian Detection
On the heavy occluded (\textbf{HO}) set of CityPerosns test set, our PSC-Net obtains an absolute gain of 4. 0\% in terms of log-average miss rate over the state-of-the-art with same backbone, input scale and without using additional VBB supervision.
Learning Compositional Neural Information Fusion for Human Parsing
The bottom-up and top-down inferences explicitly model the compositional and decompositional relations in human bodies, respectively.
NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
With this observation, we propose a new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features.
Deep Contextual Attention for Human-Object Interaction Detection
Our approach outperforms the state-of-the-art on all datasets.
Mask-Guided Attention Network for Occluded Pedestrian Detection
Our approach obtains an absolute gain of 9. 5% in log-average miss rate, compared to the best reported results on the heavily occluded (HO) pedestrian set of CityPersons test set.
Towards Bridging Semantic Gap to Improve Semantic Segmentation
By embedding these two strategies, we construct a parallel feature pyramid towards improving multi-level feature fusion.
A Semantics-Guided Class Imbalance Learning Model for Zero-Shot Classification
Towards alleviating the class imbalance issue in ZSC, we propose a sample-balanced training process to encourage all training classes to contribute equally to the learned model.
ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation
Segmentation is a fundamental task in medical image analysis.
Ranked #1 on
Optic Disc Segmentation
on REFUGE
Efficient Featurized Image Pyramid Network for Single Shot Detector
The performance of our detector is validated on two benchmarks: PASCAL VOC and MS COCO.
Saliency-Guided Attention Network for Image-Sentence Matching
Concretely, the saliency detector provides the visual saliency information as the guidance for the two attention modules.
Stacked Semantics-Guided Attention Model for Fine-Grained Zero-Shot Learning
Zero-Shot Learning (ZSL) is generally achieved via aligning the semantic relationships between the visual features and the corresponding class semantic descriptions.
Bi-Adversarial Auto-Encoder for Zero-Shot Learning
Existing generative Zero-Shot Learning (ZSL) methods only consider the unidirectional alignment from the class semantics to the visual features while ignoring the alignment from the visual features to the class semantics, which fails to construct the visual-semantic interactions well.
Triply Supervised Decoder Networks for Joint Detection and Segmentation
Experimental results on the VOC2007 and VOC2012 datasets demonstrate that the proposed TripleNet is able to improve both the detection and segmentation accuracies without adding extra computational costs.
Ranked #18 on
Semantic Segmentation
on PASCAL VOC 2012 test
Stacked Semantic-Guided Attention Model for Fine-Grained Zero-Shot Learning
To this end, we propose a novel stacked semantics-guided attention (S2GA) model to obtain semantic relevant features by using individual class semantic features to progressively guide the visual features to generate an attention map for weighting the importance of different local regions.
Exploring Multi-Branch and High-Level Semantic Networks for Improving Pedestrian Detection
In this paper, we propose a multi-branch and high-level semantic network by gradually splitting a base network into multiple different branches.
A Cascaded Convolutional Neural Network for Single Image Dehazing
Different from previous learning-based methods, we propose a flexible cascaded CNN for single hazy image restoration, which considers the medium transmission and global atmospheric light jointly by two task-driven subnetworks.
Attribute-Guided Network for Cross-Modal Zero-Shot Hashing
To address the Cross-Modal Zero-Shot Hashing (CMZSH) retrieval task, we propose a novel Attribute-Guided Network (AgNet), which can perform not only IBIR, but also Text-Based Image Retrieval (TBIR).
Simultaneously Learning Neighborship and Projection Matrix for Supervised Dimensionality Reduction
It is interesting that the optimal regularization parameter is adaptive to the neighbors in low-dimensional space and has intuitive meaning.
Video Summarization with Attention-Based Encoder-Decoder Networks
This paper addresses the problem of supervised video summarization by formulating it as a sequence-to-sequence learning problem, where the input is a sequence of original video frames, the output is a keyshot sequence.
Ranked #4 on
Video Summarization
on TvSum
(using extra training data)
Query-Aware Sparse Coding for Multi-Video Summarization
Given the explosive growth of online videos, it is becoming increasingly important to relieve the tedious work of browsing and managing the video content of interest.
Semantic Softmax Loss for Zero-Shot Learning
However, the visual features and the class semantic descriptors locate in different structural spaces, a linear or bilinear model can not capture the semantic interactions between different modalities well.
Transductive Zero-Shot Learning with Adaptive Structural Embedding
Two fundamental challenges in it are visual-semantic embedding and domain adaptation in cross-modality learning and unseen class prediction steps, respectively.
Zero-Shot Learning with Multi-Battery Factor Analysis
Zero-shot learning (ZSL) extends the conventional image classification technique to a more challenging situation where the test image categories are not seen in the training samples.
Convolution in Convolution for Network in Network
In this paper, we propose to replace dense shallow MLP with sparse shallow MLP.
Learning Multilayer Channel Features for Pedestrian Detection
For example, CNN classifies these proposals by the full-connected layer features while proposal scores and the features in the inner-layers of CNN are ignored.
Ranked #25 on
Pedestrian Detection
on Caltech
Cascaded Subpatch Networks for Effective CNNs
The first one is a linear filter of spatial size $ h\times w $ and is aimed at extracting features from spatial domain.
Pedestrian Detection Inspired by Appearance Constancy and Shape Symmetry
Finally, we propose to combine both non-neighboring and neighboring features for pedestrian detection.
Ranked #28 on
Pedestrian Detection
on Caltech
Moving Object Detection in Video Using Saliency Map and Subspace Learning
So there are undesirable false alarms and missed alarms in many algorithms of moving object detection.
Learning Sampling Distributions for Efficient Object Detection
Multistage particle windows (MPW), proposed by Gualdi et al., is an algorithm of fast and accurate object detection.
Cascade Learning by Optimally Partitioning
iCascade searches the optimal number ri of weak classifiers of each stage i by directly minimizing the computation cost of the cascade.
Efficient 2D-to-3D Correspondence Filtering for Scalable 3D Object Recognition
3D model-based object recognition has been a noticeable research trend in recent years.
