Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks197 from public data
- BMN: Boundary-Matching Network for Temporal Action Proposal Generation749
This work proposes an effective, efficient and end-to-end proposal generation method, named Boundary-Matching Network (BMN), which generates proposals with precise temporal boundaries as well as reliable confidence scores simultaneously, and can achieve state-of-the-art temporal action detection performance.
- 497
- AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer456
A novel attention and normalization module, named Adaptive Attention Normalization (AdaAttN), to adaptively perform attentive normalization on per-point basis is proposed, which achieves state-of-the-art arbitrary image/video style transfer.
- Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition426
A novel attention-based convolutional neural network (CNN) which regulates multiple object parts among different input images, which can be easily trained end-to-end, and is highly efficient which requires only one training stage.
- Student-Teacher Feature Pyramid Matching for Anomaly Detection396
This paper proposes a simple yet powerful approach to anomaly detection, which is implemented in the student-teacher framework for its advantages but substantially extends it in terms of both accuracy and efficiency.
- Towards Accurate Scene Text Recognition With Semantic Reasoning Networks384
This work proposes a novel end-to-end trainable framework named semantic reasoning network (SRN) for accurate scene text recognition, where a global semantic reasoning module (GSRM) is introduced to capture global semantic context through multi-way parallel transmission.
- 384
- ACFNet: Attentional Class Feature Network for Semantic Segmentation315
This paper presents the concept of class center which extracts the global context from a categorical perspective, and proposes a novel module, named Attentional Class Feature (ACF) module, to calculate and adaptively combine different class centers according to each pixel.
- Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes302
A novel text detector namely LOMO is presented, which localizes the text progressively for multiple times (or in other word, LOok More than Once), and the state-of-the-art results on several public benchmarks confirm the striking robustness and effectiveness of LomO.
- Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment283
Group DETR is introduced, a simple yet efficient DETR training approach that introduces a group-wise way for one-to-many assignment that speeds up the training convergence and improves the performance of various DETR-based models.
- Image Inpainting With Learnable Bidirectional Attention Maps282
This paper presents a learnable attention map module for learning feature re-normalization and mask-updating in an end-to-end manner, which is effective in adapting to irregular holes and propagation of convolution layers.
- ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT272
This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text - RRC-ArT that consists of three major challenges: i) scene text detection, ii) sceneText recognition, and iii) scenetext spotting.
- A Mutual Learning Method for Salient Object Detection With Intertwined Multi-Supervision255
This work proposes to train saliency detection networks by exploiting the supervision from not only salient object detection, but also foreground contour detection and edge detection, and develops a novel mutual learning module (MLM), which improves the performance by a large margin.
- 223
- Dynamic Instance Normalization for Arbitrary Style Transfer222
The proposed Dynamic Instance Normalization (DIN) provides flexible support for state-of-the-art convolutional operations, and thus triggers novel functionalities, such as uniform-stroke placement for non-natural images and automatic spatial-stroke control.
- Perspective-Guided Convolution Networks for Crowd Counting217
A novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i.e. PGCNet) is proposed, which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect.
- WordSup: Exploiting Word Annotations for Character Based Text Detection209
A weakly supervised framework that can utilize word annotations, either in tight quadrangles or the more loose bounding boxes, for character detector training is proposed, able to train a robust character detector by exploiting word annotations in the rich large-scale real scene text datasets, e.g. ICDAR15 and COCO-text.
- ICDAR 2019 Competition on Large-Scale Street View Text with Partial Labeling - RRC-LSVT207
This competition aims to explore the abilities of state-of-the-art methods to detect and recognize text instances from large-scale street view images, closing gaps between research benchmarks and real applications.
- Rope3D: The Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task182
The first high-diversity challenging Roadside Perception 3D dataset- Rope3D from a novel view is presented, which tailor the existing frontal-view monocular 3D object detection approaches and propose to leverage the geometry constraint to solve the inherent ambiguities caused by various sensors, viewpoints.
- Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement177
A novel framework that generates textured surface meshes from images by efficiently initializing the geometry and view-dependency decomposed appearance with a NeRF and adapting both vertex positions and face density based on reprojected rendering errors is presented.
- Editing Text in the Wild171
This work proposes an end-to-end trainable style retention network (SRNet) that consists of three modules: text conversion module, background inpainting module and fusion module, which is the first attempt to edit text in natural images at the word level.
- 165
- StrucTexT: Structured Text Understanding with Multi-Modal Transformers157
This paper proposes a unified framework named StrucTexT, which is flexible and effective for handling both sub-tasks, and introduces a segment-token aligned encoder to deal with the entity labeling and entity linking tasks at different levels of granularity.
- MixFormer: Mixing Features across Windows and Dimensions152
This work combines local-window self-attention with depth-wise convolution in a parallel design, modeling cross-window connections to enlarge the receptive fields and proposes bi-directional interactions across branches to provide complementary clues in the channel and spatial dimensions.
- DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features148
This paper proposes a Deep Orthogonal Local and Global (DOLG) information fusion framework for end-to-end image retrieval that achieves state-of-the-art image retrieval performances on Revisited Oxford and Paris datasets.
- Implicit Sample Extension for Unsupervised Person Re-Identification144
An Implicit Sample Extension method to generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy, which reduces the “sub and mixed” clustering errors, thus improving the Re-ID performance.
- VRP-SAM: SAM with Visual Reference Prompt131
A novel Visual Reference Prompt encoder that empowers the Segment Any-thing Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model, which achieves a breakthrough within the SAM framework by extending its versatility and applicabil-ity while preserving SAM's inherent strengths, thus enhancing user-friendliness.
- StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator125
This paper designs a mask-guided spatial information encoding module that preserves the details of the given face and enables personalized lip-sync by introducing style space and generator refinement on only limited frames, so the identity and talking style of a target person could be accurately preserved.
- 118
- Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement116
A two-stage graph-based and model-agnostic framework, called Graph-PCNN, with a localization subnet and a graph pose refinement module added onto the original heatmap regression network to get more accurate localization results.
- Paint Transformer: Feed Forward Neural Painting with Stroke Prediction112
This paper formulate the task as a set prediction problem and proposes a novel Transformer-based framework, dubbed Paint Transformer, to predict the parameters of a stroke set with a feed forward network, which achieves better painting performance than previous ones with cheaper training and inference costs.
- Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer111
Inspired by the common painting process of drawing a draft and revising the details, a novel feed-forward method named Laplacian Pyramid Network (LapStyle) is introduced that can synthesize high quality stylized images in real time, where holistic style patterns are properly transferred.
- NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results106
This paper reviews the NTIRE 2020 challenge on real image denoising with focus on the newly introduced dataset, the proposed methods and their results, based on the SIDD benchmark.
- PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network105
The PGNet is a single-shot text spotter, where the pixel-level character classification map is learned with proposed PG-CTC loss avoiding the usage of character-level annotations, and a graph refinement module (GRM) is proposed to optimize the coarse recognition and improve the end-to-end performance.
- Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection104
A domain adaptation like approach is innovatively proposed to enhance the robustness of the feature representation in 3D object detection and mimics the functionality of the human brain when proceeding object perception.
- 102
- MS-DETR: Efficient DETR Training with Mixed Supervision97
Experimental results show that the MS-DETR approach outperforms related DETR variants, such as DN-DETR, Hybrid DETR, and Group DETR, and the combination with related DETR variants further improves the performance.
- Unsupervised Multi-Source Domain Adaptation for Person Re-Identification96
The proposed method outperforms state-of-the-art UDA person re-ID methods by a large margin, and even achieves comparable performance to the supervised approaches without any post-processing techniques.
- Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition94
A novel multi-granular spatio-temporal graph network is proposed for skeleton-based action classification that jointly models the coarse- and fine-grained skeleton motion patterns and utilises a cross-head communication strategy to mutually enhance the representations of both heads.
- MVFNet: Multi-View Fusion Network for Efficient Video Recognition94
A novel multi-view fusion (MVF) module is introduced to exploit video dynamics using separable convolution for efficiency and the proposed MVFNet can achieve state-of-the-art performance with 2D CNN's complexity.
- Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition91
An attribute-guided attention localization scheme where the local region localizers are learned under the guidance of part attribute descriptions is introduced, which is more amenable than the accurate part location annotation required by traditional part-based fine-grained recognition methods.
- Forward Flow for Novel View Synthesis of Dynamic Scenes90
Thorough experiments show that the proposed neural radiance field approach outperforms existing methods in both novel view rendering and motion modeling, demonstrating the effectiveness of the forward flow motion modeling.
- Few-Shot Font Generation by Learning Fine-Grained Local Styles89
A new font generation approach by learning the fine-grained local styles from references, and the spatial correspondence between the content and reference glyphs, which outperforms the state-of-the-art methods in FFG.
- Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video88
A dual-branch network is proposed which takes as input the proposals with multi-granularities in both spatial-temporal domains and progressively refines the corresponding branch and the whole framework, set up to employ dual-path mutual guidance in a recurrent manner.
- Semi-DETR: Semi-Supervised Object Detection with Detection Transformers87
This work proposes a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one- to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage.
- Human-Object Interaction Detection via Disentangled Transformer87
This work decouple the triplet prediction into human-object pair detection and interaction classification, and presents Disentangled Transformer, where both encoder and decoder are disentangled to facilitate learning of two sub-tasks.
- MobileFaceSwap: A Lightweight Framework for Video Face Swapping87
A lightweight Identity-aware Dynamic Network (IDN) is proposed for subject-agnostic face swapping by dynamically adjusting the model parameters according to the identity information by introducing two dynamic neural network techniques, including the weights prediction and weights modulation.
- ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval86
A novel fusion token based transformer aggregation approach to exchange the necessary scene text information only through the fusion token and concentrate on the most important features in each modality to tackle the modality missing problem of scene text.
- Segment as Points for Efficient Online Multi-Object Tracking and Segmentation85
This paper proposes a highly effective method for learning instance embeddings based on segments by converting the compact image representation to un-ordered 2D point cloud representation and builds a more challenging MOTS dataset named APOLLO MOTS with higher instance density.
- A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning80
This paper proposes a novel segmentation-based text detector, namely SAST, which employs a context attended multi-task learning framework based on a Fully Convolutional Network to learn various geometric properties for the reconstruction of polygonal representation of text regions.
- ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection78
A novel framework named ZoomNet for stereo imagery-based 3D detection, which surpasses all previous state-of-the-art methods by large margins and introduces to learn part locations as complementary features to improve the resistance against occlusion and put forward the 3D fitting score to better estimate the3D detection quality.
- 68
- Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection67
A Ambiguity-Resistant Semi-supervised Learning (ARSL) for one-stage detectors is proposed that effectively mitigates the ambiguities and achieves state-of-the-art SSOD performance on MS COCO and PASCAL VOC.
- The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection67
This paper digs into the 3D object detection task and reformulate it as the sub-tasks of object localization and appearance perception, which benefits to a deep excavation of reciprocal information underlying the entire task.
- TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network66
An end-to-end trainable network architecture, named TextNet, is proposed, which is able to simultaneously localize and recognize irregular text from images, and can achieve state-of-the-art performance on irregular datasets by a large margin.
- 65
- Chinese Street View Text: Large-Scale Chinese Text Reading With Partially Supervised Learning63
A text reading network in a partially supervised learning framework, which enables to localize and recognize text, learn from fully and weakly annotated data simultaneously, and localize the best matched text proposals from weakly labeled images is designed.
- CAPE: Camera View Position Embedding for Multi-View 3D Object Detection60
This paper proposes a novel method based on CAmera view Position Embedding, called CAPE, which form the 3D position embed-dings under the local camera-view coordinate system instead of the global coordinate system, such that3D position em-bedding is free of encoding camera extrinsic parameters.
- EATEN: Entity-Aware Attention for Single Shot Visual Text Extraction60
This paper proposes an Entity-aware Attention Text Extraction Network called EATEN, which is an end-to-end trainable system to extract the ToIs without any post-processing, and is the first single shot method to extract entities from images.
- Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation58
The approach without human box supervision is superior to previous methods with complex decoders, and even is slightly better than ED-Pose that uses human box supervision.
- 58
- ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency56
It is observed that the consistency between positive samples is the key to learn robust video representations and two tasks to learn appearance and speed consistency are proposed, separately.
- Multi-camera vehicle tracking and re-identification based on visual and spatial-temporal features54
A novel framework for multi-camera tracking, which integrates visual features, orientation prediction and temporal-spatial information of the trajectories for optimization is proposed, which achieves the first place in vehicle re-identification at the NVIDIA AI City Challenge 2019.
- PSVT: End-to-End Multi-Person 3D Pose and Shape Estimation with Progressive Video Transformers53
A new end-to-end multi-person 3D Pose and Shape estimation framework with progressive Video Transformer, termed PSVT, and a novel pose-guided attention (PGA) for shape decoder to better predict shape parameters are proposed to improve performance.
- FaceController: Controllable Attribute Editing for Face in the Wild53
This work proposes a simple feed-forward network to generate high-fidelity manipulated faces with one or multiple desired face attributes manipulated while other details are preserved by simply employing some existing and easy-obtainable prior information.
- Group Re-Identification53
Multi-grain representations are computed to characterize the appearance and spatial features of multi-grain objects and evaluate the importance weight of each object for group Re-ID, so as to handle the interferences from group dynamics.
- Fine-Grained Video Categorization with Redundancy Reduction Attention53
A new network structure, known as Redundancy Reduction Attention (RRA), which learns to focus on multiple discriminative patterns by suppressing redundant feature channels by learning which channels to suppress or to enhance with a learned non-linear transform.
- 51
- Monocular 3D Object Detection via Feature Domain Adaptation50
A novel domain adaptation based monocular 3D object detection framework named DA-3Ddet is proposed, which adapts the feature from unsound image-based pseudo-LiDAR domain to the accurate real LiDAR domain for performance boosting and introduces a context-aware foreground segmentation module.
- Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model49
A novel framework, i.e., Predict, Prevent, and Evaluate (PPE), for disentangled text-driven image manipulation that requires little manual annotation while being applicable to a wide variety of ma-nipulations.
- 47
- AGO-Net: Association-Guided 3D Point Cloud Object Detection Network45
This work introduces an attention-based re-weighting module that adaptively strengthens the feature adaptation of more informative regions and achieves new state-of-the-art performance on the KITTI 3D detection benchmark in both accuracy and speed.
- 44
- 43
- AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results43
This paper introduces the real image Super-Resolution challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020, and gauges the state-of-the-art approaches for real image SR in terms of PSNR and SSIM.
- Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence42
The proposed method is the first to treat arbitrary rescaling, both upscaling and downscaling, as one unified process, and is able to learn up Scaling and Downscaling simultaneously and achieve bidirectional arbitrary image rescaling.
- 39
- 38
- 38
- 37
- 36
- Multi-Domain Incremental Learning for Face Presentation Attack Detection35
An adaptive domain-specific experts (ADE) framework based on the vision transformer to preserve the discriminability of previous domains and an asymmetric classifier is designed to keep the output distribution of different classifiers consistent, thereby improving the generalization ability.
- 35
- 34
- 32
- LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution32
A new baseline method for multi-reference super-resolution is proposed: MRefSR, including a Multi-Reference Attention Module (MAM) for feature fusion of an arbitrary number of reference images, and a Spatial Aware Filtering Module (SAFM) for the fused feature selection.
- Few-Shot Head Swapping in the Wild32
This paper presents the Head Swapper (HeSer), which achieves few-shot head swapping in the wild through two delicately de-signed modules, and demonstrates that the proposed method produces superior head swapping results on a variety of scenes.
- 32
- 31
- 31
- Adversarial Dual-Student With Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation30
A context friendly differentiable geometric warping to conduct unsupervised data augmentation and a novel adversarial dual-student framework is proposed to improve the Mean-Teacher from the following two aspects.
- 29
- 29
- 27
- 26
- 26
- 25
- 24
- 24
- 23
- 23
- 23
- 22
- 22
- 22
- 21
- 21
- 20
- 20
- 20
- 19
- 19
- 18
- 18
- 17
- 17
- 15
- 15
- 15
- 14
- 14
- 14
- 13
- 13
- 13
- 13
- 13
- 12
- 12
- 12
- 11
- 11
- 11
- 10
- 9
- 9
- 9
- 9
- 9
- 8
- 8
- 8
- ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts7
ALoRE is proposed, a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts using a multi-branch paradigm, disentangling the learned cognitive patterns during training.
- 7
- 6
- 6
- 6
- 6
- 6
- 6
- 6
- 5
- 5
- 5
- 5
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- Add-SD: Rational Generation without Manual Reference2
An instruction-based object addition pipeline, named Add-SD, which automatically inserts objects into realistic scenes with rational sizes and positions is introduced, which is solely conditioned on simple text prompts rather than any other human-costly references like bounding boxes.
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-13. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it.