Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks103 from public data
- Cost-Effective Active Learning for Deep Image Classification756
This paper proposes a novel active learning (AL) framework, which is capable of building a competitive classifier with optimal feature representation via a limited amount of labeled training instances in an incremental learning manner and incorporates deep convolutional neural networks into AL.
- DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images446
A strong baseline is proposed, called Match R- CNN, which builds upon Mask R-CNN to solve the above four tasks in an end-to-end manner to address issues of DeepFashion2.
- Shallow Attention Network for Polyp Segmentation443
The Shallow Attention Network (SANet) is proposed, which design the color exchange operation to decouple the image contents and colors, and force the model to focus more on the target shape and structure, and the shallow attention module to filter out the background noise of shallow features.
- Sparse Single Sweep LiDAR Point Cloud Segmentation via Learning Contextual Shape Priors from Scene Completion400
A novel sparse LiDAR point cloud semantic segmentation framework assisted by learned contextual shape priors is proposed, which inherently improves SS optimization through fully end-to-end training.
- Towards Photo-Realistic Virtual Try-On by Adaptively Generating↔Preserving Image Content347
This work proposes a novel visual try-on network, namely Adaptive Content Generating and Preserving Network (ACGPN), which can generate photo-realistic images with much better perceptual quality and richer fine-details.
- 327
- 278
- Parser-Free Virtual Try-on via Distilling Appearance Flows267
This work proposes a novel approach, "teacher-tutor-student" knowledge distillation, which is able to produce highly photo-realistic images without human parsing, possessing several appealing advantages compared to prior arts.
- 262
- End-to-End Dense Video Captioning with Parallel Decoding260
Without bells and whistles, extensive experiments show that PDVC is capable of producing high-quality captioning results, surpassing the state-of-the-art two-stage methods when its localization accuracy is on par with them.
- InstanceRefer: Cooperative Holistic Understanding for Visual Grounding on Point Clouds through Instance Multi-level Contextual Referring214
The non-trivial 3D visual grounding task has been effectively re-formulated as a simplified instance-matching problem, considering that instance-level candidates are more rational than the redundant 3D object proposals.
- SmartEdit: Exploring Complex Instruction-Based Image Editing with Multimodal Large Language Models213
A Bidirectional Interaction Module (BIM) is proposed that enables comprehensive bidirectional information interactions between the input image and the MLLM output and demonstrates that a small amount of complex instruction editing data can effectively stimulate SmartEdit’ s editing capabilities for more complex instructions.
- Multi-compound Transformer for Accurate Biomedical Image Segmentation187
A unified transformer network, termed Multi-Compound Transformer (MCTrans), which incorporates rich feature learning and semantic structure mining into a unified framework and performs intra- and inter-scale self-attention, rather than single-scale attention in previous works.
- SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension156
SEED-Bench-2-Plus is introduced, a benchmark specifically designed for evaluating text-rich visual comprehension of Multimodal Large Language Models and a thorough evaluation involving 34 prominent MLLMs is conducted, to emphasize the current limitations of MLLMs in text-rich visual comprehension.
- 148
- Switchable Normalization for Learning-to-Normalize Deep Representation104
Switchable Normalization (SN), which learns to select different normalizers for different normalization layers of a deep neural network, is proposed and will help ease the usage and understand the normalization techniques in deep learning.
- SEED-Bench-2: Benchmarking Multimodal Large Language Models103
This work categorizes the capabilities of MLLMs into hierarchical levels from $L_0 to $L-4 based on the modalities they can accept and generate, and proposes SEED-Bench-2, a comprehensive benchmark that evaluates the hierarchical capabilities ofMLLMs.
- SCAN: Self-and-Collaborative Attention Network for Video Person Re-Identification92
A novel and practical deep architecture for video person re-identification termed self-and-collaborative attention network (SCAN), which adopts the video pairs as the input and outputs their matching scores and can be predicted by the binary classifier.
- AIM 2020 Challenge on Learned Image Signal Processing Pipeline90
This paper reviews the second AIM learned ISP challenge and provides the description of the proposed solutions and results, defining the state-of-the-art for practical image signal processing pipeline modeling.
- 87
- PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond85
The proposed polar representation can provide a new perspective for designing algorithms to solve single-shot instance segmentation, and is fully convolutional and can be easily embedded into most off-the-shelf detection methods.
- Attentive Crowd Flow Machines75
A unified neural network module, called Attentive Crowd Flow Machine~ (ACFM), which is able to infer the evolution of the crowd flow by learning dynamic representations of temporally-varying data with an attention mechanism, and achieves significant improvements over the state-of-the-art methods.
- SSN: Learning Sparse Switchable Normalization via SparsestMax57
Sparse switchable normalization (SSN) is presented where the importance ratios are constrained to be sparse, and SparsestMax is a sparse version of softmax, which is guaranteed to select only one normalizer for each normalization layer, avoiding redundant computations and improving interpretability of normalizer selection.
- 50
- Weakly Supervised Object Localization via Transformer with Implicit Spatial Calibration49
A simple yet effective Spatial Calibration Module (SCM) is introduced for accurate WSOL, incorporating semantic similarities of patch tokens and their spatial relationships into a unified diffusion model, and introduces a learnable parameter to dynamically adjust the semantic correlations and spatial context intensities for effective information propagation.
- 41
- Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks40
This work presents Groupable ConvNet (GroupNet) built by using a novel dynamic grouping convolution (DGConv) operation, which is able to learn the number of groups in an end-to-end manner and outperforms its counterparts such as ResNet and ResNeXt in terms of accuracy and computational complexity.
- Boosting Human-Object Interaction Detection with Text-to-Image Diffusion Model37
DiffHOI is introduced, a novel HOI detection scheme grounded on a pre-trained text-image diffusion model, which enhances the detector's performance via improved data diversity and HOI representation, and SynHOI, a class-balance, large-scale, and high-diversity synthetic dataset containing over 140K HOI images with fully triplet annotations.
- SupFusion: Supervised LiDAR-Camera Fusion for 3D Object Detection36
A novel training strategy called SupFusion is proposed, which provides an auxiliary feature level supervision for effective LiDAR-Camera fusion and significantly boosts detection performance and a simple yet effective deep fusion module, which contiguously gains superior performance compared with previous fusion methods with SupFusion strategy.
- Multi-Stage Spatio-Temporal Aggregation Transformer for Video Person Re-Identification34
A novel Multi-Stage Spatial-Temporal Aggregation Transformer with two novel designed proxy embedding modules to address the critical issue of extracting local attributes and global identity information for the person re-identification task.
- Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once33
This paper proposes the first Multi-target Adversarial Network (MAN), which can generate multi-target adversarial samples with a single model and can achieve better classification accuracy than other methods when attacked by various methods.
- Deep Structured Scene Parsing by Learning with Image Descriptions33
This paper proposes a deep architecture consisting of a convolutional neural network extracting the image representation for pixelwise object labeling and a recursive neural network discovering the hierarchical object structure and the inter-object relations and decomposes each sentence into a semantic tree.
- UXNet: Searching Multi-level Feature Aggregation for 3D Medical Image Segmentation28
This paper proposes a novel NAS method for 3D medical image segmentation, named UXNet, which searches both the scale-wise feature aggregation strategies as well as the block-wise operators in the encoder-decoder network.
- 26
- 26
- 26
- 24
- 22
- 22
- Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains21
Experimental results demonstrate SST can effectively achieve promising universal human parsing performance as well as impressive improvements compared to its counterparts on three human parsing benchmarks (i.e., PASCAL-Person-Part, ATR, and CIHP).
- 19
- 19
- Exemplar Normalization for Learning Deep Representation18
This work investigates a novel dynamic learning-to-normalize (L2N) problem by proposing Exemplar Normalization (EN), which is able to learn different normalization methods for different convolutional layers and image samples of a deep network.
- 16
- 16
- 16
- 15
- Toward Unpaired Multi-modal Medical Image Segmentation via Learning Structured Semantic Consistency15
This paper presents a novel scheme to learn the mutual benefits of different modalities to achieve better segmentation results for unpaired multi-modal medical images, designed as an external plug-and-play one, which can be discarded once the model is optimized.
- 13
- 12
- 12
- 11
- Hierarchical Weight Averaging for Deep Neural Networks9
This work first attempts to incorporate online and offline WA into a general training framework termed hierarchical WA, which is able to achieve both faster convergence speed and superior generalization performance without any fancy learning rate adjustment.
- 9
- PointLIE: Locally Invertible Embedding for Point Cloud Sampling and Recovery9
A novel Locally Invertible Embedding (PointLIE) framework is proposed to unify the point cloud sampling and upsampling into one single framework through bi-directional learning and can theoretically guarantee the fidelity of reconstruction and outperform state-of-the-arts quantitatively and qualitatively.
- 9
- 8
- 8
- Story3D-Agent: Exploring 3D Storytelling Visualization with Large Language Models8
This work presents Story3D-Agent, a pioneering approach that leverages the capabilities of LLMs to transform provided narratives into 3D-rendered visualizations, and enables precise control over multi-character actions and motions, as well as diverse decorative elements, ensuring the long-range and dynamic 3D representation.
- 8
- 7
- 6
- 5
- Polygon-Free: Unconstrained Scene Text Detection with Box Annotations5
An unconstrained text detection system termed Polygon-free (PF), in which most existing polygon-based text detectors are trained with only upright bounding box annotations, to transfer knowledge from synthetic data to real data to enhance the supervision information of upright bounded boxes.
- 4
- 4
- SelfText Beyond Polygon: Unconstrained Text Detection with Box Supervision and Dynamic Self-Training.4
A novel text detection system termed SelfText Beyond Polygon (SBP) with Bounding Box Supervision (BBS) and Dynamic Self Training (DST), where training a polygon-based text detector with only a limited set of upright bounding box annotations is proposed.
- 4
- 3
- 3
- 3
- 3
- 3
- 3
- 2
- 2
- 2
- SR-OOD: Out-of-Distribution Detection via Sample Repairing2
This work takes advantage of sample repairing and proposes a novel OOD detection framework, namely SR-OOD, that leverages the idea that repairing an OOD sample can reveal its semantic inconsistency with the in-distribution data.
- 2
- 2
- 2
- 2
- 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.