Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks189 from public data
- BiSeNet: Bilateral Segmentation Network for Real-Time Semantic Segmentation2,800
A novel Bilateral Segmentation Network (BiSeNet) is proposed that makes a right balance between the speed and segmentation performance on Cityscapes, CamVid, and COCO-Stuff datasets.
- Cascaded Pyramid Network for Multi-person Pose Estimation1,795
A novel network structure called Cascaded Pyramid Network (CPN) is presented which targets to relieve the problem from these "hard" keypoints, with state-of-art results on the COCO keypoint benchmark, with average precision at 73.0.
- BiSeNet V2: Bilateral Network with Guided Aggregation for Real-Time Semantic Segmentation1,770
This work proposes an efficient and effective architecture with a good trade-off between speed and accuracy, termed Bilateral Segmentation Network (BiSeNet V2), and designs a guided aggregation layer to enhance mutual connections and fuse both types of feature representation.
- Large Kernel Matters — Improve Semantic Segmentation by Global Convolutional Network1,669
This work proposes a Global Convolutional Network to address both the classification and localization issues for the semantic segmentation and suggests a residual-based boundary refinement to further refine the object boundaries.
- 1,124
- SiamFC++: Towards Robust and Accurate Visual Tracking with Target Estimation Guidelines982
This work proposes a set of practical guidelines of target state estimation for high-performance generic object tracker design and designs the Fully Convolutional Siamese tracker++ (SiamFC++), which achieves state-of-the-art performance on five challenging benchmarks, which proves both the tracking and generalization ability of the tracker.
- Learning a Discriminative Feature Network for Semantic Segmentation870
This work proposes a Discriminative Feature Network (DFN), which contains two sub-networks: Smooth Network and Border Network, which is specially design to handle the intra-class inconsistency problem and to make the bilateral features of boundary distinguishable with deep semantic boundary supervision.
- Shape Robust Text Detection With Progressive Scale Expansion Network860
A novel Progressive Scale Expansion Network (PSENet) is proposed, which can precisely detect text instances with arbitrary shapes and is effective to split the close text instances, making it easier to use segmentation-based methods to detect arbitrary-shaped text instances.
- Executing your Commands via Motion Diffusion in Latent Space766
The proposed Motion Latent-based Diffusion model (MLD) could produce vivid motion sequences conforming to the given conditional inputs and substantially reduce the computational overhead in both the training and inference stages.
- Efficient and Accurate Arbitrary-Shaped Text Detection With Pixel Aggregation Network631
This paper proposes an efficient and accurate arbitrary-shaped text detector, termed Pixel Aggregation Network (PAN), which is equipped with a low computational-cost segmentation head and a learnable post-processing.
- AppAgent: Multimodal Agents as Smartphone Users555
A novel LLM-based multimodal agent framework designed to operate smartphone applications that allows the agent to mimic human-like interactions such as tapping and swiping through a simplified action space, eliminating the need for system back-end access and enhancing its versatility across various apps.
- High-Order Information Matters: Learning Relation and Topology for Occluded Person Re-Identification512
This paper proposes a novel framework by learning high-order relation and topology information for discriminative features and robust alignment for occluded person re-identification and significantly outperforms state-of-the-art mAP scores on Occluded-Duke dataset.
- 462
- MegDet: A Large Mini-Batch Object Detector338
This paper proposes a Large Mini-Batch Object Detector (MegDet) to enable the training with a large minibatch size up to 256, so that it can effectively utilize at most 128 GPUs to significantly shorten the training time.
- TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation337
Experimental results demonstrate that the proposed TopFormer method significantly outperforms CNN- and ViT-based networks across several semantic segmentation datasets and achieves a good trade-off between accuracy and latency.
- DetNet: Design Backbone for Object Detection337
DetNet is proposed, which is a novel backbone network specifically designed for object detection that includes the extra stages against traditional backbone network for image classification, while maintains high spatial resolution in deeper layers.
- Context Prior for Scene Segmentation302
This work develops a Context Prior with the supervision of the Affinity Loss, an effective Context Prior Network that can selectively capture the intra-class and inter-class contextual dependencies, leading to robust feature representation.
- 297
- ThunderNet: Towards Real-Time Generic Object Detection on Mobile Devices292
benefit from the highly efficient backbone and detection part design, ThunderNet surpasses previous lightweight one-stage detectors with only 40% of the computational cost on PASCAL VOC and COCO benchmarks.
- LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning290
LL3DA is presented, a Large Language 3D Assistant that takes point cloud as the direct input and responds to both text instructions and visual interactions that enables LMMs to better comprehend human interactions with the 3D environment and further remove the ambiguities within plain texts.
- 259
- Scene Text Detection with Supervised Pyramid Context Network238
A supervised pyramid context network (SPCNET) is proposed to precisely locate text regions while suppressing false positives in scene text detection, based on Feature Pyramid Network (FPN) and instance segmentation.
- 223
- 216
- Human pose estimation and its application to action recognition: A survey175
This survey focuses on 2D skeleton-based action recognition where the human poses are estimated from regular RGB images instead of depth images, and summarizes the performance of recent action recognition methods that use pose estimated from color images as input, showing that there is much room for improvements in this direction.
- Modeling Local Geometric Structure of 3D Point Clouds Using Geo-CNN166
The proposed Geo-CNN applies a generic convolution-like operation dubbed as GeoConv to each point and its local neighborhood, which encourages the network to preserve the geometric structure in Euclidean space throughout the feature extraction hierarchy.
- Attention-Based Multi-Context Guiding for Few-Shot Semantic Segmentation165
An Attentionbased Multi-Context Guiding (A-MCG) network is proposed, which consists of three branches: the support branch, the query branch, the feature fusion branch, and adopts a spatial attention along the fusion branch to highlight context information from several scales, enhancing self-supervision in one-shot learning.
- Paint3D: Paint Anything 3D With Lighting-Less Texture Diffusion Models163
Through this coarse-to-fine process, Paint3D can produce high-quality 2K UV textures that maintain se-mantic consistency while being lighting-less, significantly advancing the state-of-the-art in texturing 3D objects.
- Discriminative Orderlet Mining for Real-Time Recognition of Human-Object Interaction160
This paper presents a novel visual representation, called orderlets, for real-time human action recognition with depth sensors, that is insensitive to small noise since an orderlet only depends on the comparative relationship among individual features.
- An End-To-End Network for Panoptic Segmentation151
A novel end-to-end Occlusion Aware Network (OANet) for panoptic segmentation is proposed, which can efficiently and effectively predict both the instance and stuff segmentation in a single network and introduces a novel spatial ranking module to deal with the occlusion problem between the predicted instances.
- 131
- State-Aware Tracker for Real-Time Video Object Segmentation126
This work proposes a novel pipeline called State-Aware Tracker (SAT), which can produce accurate segmentation results with real-time speed and takes advantage of the inter-frame consistency and deals with each target object as a tracklet.
- 119
- End-to-End 3D Dense Captioning with Vote2Cap-DETR112
Without bells and whistles, extensive experiments on two commonly used datasets, ScanRefer and Nr3D, demonstrate that the proposed Vote2Cap-DETR surpasses current state-of-the-arts by 11.13% and 7.11% in CIDEr@0.5IoU, respectively.
- Associating Inter-image Salient Instances for Weakly Supervised Semantic Segmentation101
This paper uses an instance-level salient object detector to automatically generate salient instances (candidate objects) for training images, and proposes a graph-partitioning-based clustering algorithm that outperforms state-of-the-art weakly supervised alternatives by a large margin.
- 94
- TACNet: Transition-Aware Context Network for Spatio-Temporal Action Detection93
The proposed TACNet can substantially improve the performance of spatio-temporal action detection and obtains competitive performance on JHMDB and significantly outperforms the state-of-the-art methods on the untrimmed UCF101 24 in terms of both frame-m AP and video-mAP.
- 89
- 86
- Randomized Spatial Partition for Scene Recognition84
The objective is to characterize the image layout by various patterns, in the form of randomized spatial partition (RSP), which makes it possible to mine the most descriptive image layout pattern for each category of scenes, and then combine them by training a discriminative classifier, i.e., the proposed ORSP classifier.
- STAR Loss: Reducing Semantic Ambiguity in Facial Landmark Detection81
A Self-adapTive Ambiguity Reduction (STAR) loss is proposed by exploiting the properties of se-mantic ambiguity to solve the semantic ambiguity problem in deep learning-based facial landmark detection.
- Wastewater surveillance for 168 pharmaceuticals and metabolites in a WWTP: Occurrence, temporal variations and feasibility of metabolic biomarkers for intake estimation65
The results support that not all the metabolites can be employed as biomarkers for back-calculation when the in-sewer stability of these compounds is unclear, such as metoprolol acid and O-desmethyl venlafaxine.
- Propagative Hough Voting for Human Activity Recognition63
The proposed activity recognition method does not rely on human detection and tracking, and can well handle the scale and intra-class variations of the activity patterns, and outperforms the state-of-the-art techniques when there is sufficient training data.
- Predicting human activities using spatio-temporal structure of interest points60
A new random forest structure is proposed, called multi-class balanced random forest, which makes a good trade-off between the balance of the trees and the discriminative abilities and significantly outperforms the state of the arts for the human activity prediction problem.
- A Large-Scale Outdoor Multi-modal Dataset and Benchmark for Novel View Synthesis and Implicit Scene Reconstruction58
A large-scale outdoor multi-modal dataset, OMMO dataset, containing complex objects and scenes with calibrated images, point clouds and prompt annotations is proposed, establishing a new benchmark for several outdoor NeRF-based tasks, such as novel view synthesis, diverse 3D representation, and multi-modal NeRF.
- Vote2Cap-DETR++: Decoupling Localization and Describing for End-to-End 3D Dense Captioning55
This paper proposes Vote2Cap-DETR, a simple-yet-effective transformer framework that decouples the decoding process of caption generation and object localization through parallel decoding, and proposes an advanced version, Vote2Cap-DETR++, which decouples the queries into localization and caption queries to capture task-specific features.
- 52
- Object-aware Long-short-range Spatial Alignment for Few-Shot Fine-Grained Image Classification42
This work proposes an object-aware long-short-range spatial alignment approach, which is composed of a foreground object feature enhancement (FOE) module, a long-range semantic correspondence (LSC) module and a short-rangeatial manipulation (SSM) module that is developed to weaken background disturbance and encourage higher foreground object response.
- MVPaint: Synchronized Multi-View Diffusion for Painting Anything 3D41
This work proposes a novel generation-refinement 3D texturing framework called MVPaint, which can generate high-resolution, seamless textures while emphasizing multi-view consistency and surpasses existing state-of-the-art methods in texturing.
- NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video: Dataset, Methods and Results41
This paper reviews the NTIRE 2022 Challenge on Super-Resolution and Quality Enhancement of Compressed Video and proposed the LDV 2.0 dataset, which includes theLDV dataset (240 videos) and 95 additional videos.
- Fast and Accurate Single-Image Depth Estimation on Mobile Devices, Mobile AI 2021 Challenge: Report39
This paper introduces the first Mobile AI challenge, where the target is to develop an end-to-end deep learning-based depth estimation solutions that can demonstrate a nearly realtime performance on smartphones and IoT platforms.
- 38
- 37
- 37
- R-FCN++: Towards Accurate Region-Based Fully Convolutional Networks for Object Detection36
This paper involves Global Context Module to improve the classification score maps by adopting large, separable convolutional kernels and introduces a new pooling method to better extract scores from the score maps, by using row-wise or column-wise max pooling.
- Stability and WBE biomarkers possibility of 17 antiviral drugs in sewage and gravity sewers33
An analytical method for quantification of 17 typical antiviral drugs was developed, and the stability of target compounds in sewer through 4 laboratory-scale gravity sewer reactors was investigated, highlighting the potential importance of flow velocity for compound stability.
- 33
- RDAU-Net: Based on a Residual Convolutional Neural Network With DFP and CBAM for Brain Tumor Segmentation33
Experimental results show that RDAU-Net achieves state-of-the-art performance, and a CBAM with channel attention and spatial attention facilitates the combination of more expressive feature information, thereby leading to more efficient extraction of contextual information from images of various scales.
- 32
- 29
- 28
- 27
- 25
- 25
- 23
- 23
- 22
- 21
- Real-time human action search using random forest based hough voting21
This paper proposes a novel framework for action retrieval which performs pattern matching at subvolume level and is very efficient in handling large corpus of videos and presents action search experiments on challenging datasets to validate the efficiency and effectiveness of the system.
- 19
- 19
- Attribute-specific Control Units in StyleGAN for Fine-grained Image Manipulation18
This work proposes a simple yet effective method to detect attribute-specific control units, which consist of multiple channels of feature maps and modulation styles and collaboratively manipulate the modulation style channels and feature maps in control units rather than individual ones to obtain the semantic and spatial disentangled controls.
- 18
- 16
- 13
- 13
- 12
- 12
- 12
- 11
- 11
- 10
- 10
- 10
- 8
- 8
- 8
- 8
- 8
- 7
- 7
- 7
- 7
- 6
- 6
- 6
- 5
- 5
- PM-INR: Prior-Rich Multi-Modal Implicit Large-Scale Scene Neural Representation5
This work explores using multi-modal priors to assist individual points to obtain more global semantic information and proposes a priorrich multi-modal implicit neural representation network, Pm-INR, for the outdoor unbounded large-scale scene.
- 5
- 5
- 5
- 4
- Disentangled Pre-training for Image Matting4
Extensive experimental evaluations show that the proposed approach outperforms both the state-of-the-art matting methods and other alternative self-supervised initialisation approaches by a large margin, and shows the robustness of the proposed approach over different backbone architectures.
- Lightweight Model Pre-Training via Language Guided Knowledge Distillation4
This paper introduces language guidance to the distillation process and proposes a new method named Language-Guided Distillation (LGD) system, which uses category names of the target downstream task to help refine the knowledge transferred between the teacher and student.
- 4
- 4
- 4
- 4
- 4
- 3
- 3
- 3
- VQ-NeRF: Vector Quantization Enhances Implicit Neural Representations3
This work proposes VQ-NeRF, an effective and efficient pipeline for enhancing implicit neural representations via vector quantization, and designs an innovative multi-scale NeRF sampling scheme that concurrently optimizes the NeRF model at both compressed and original scales to enhance the network's ability to preserve fine details.
- 3
- 3
- 3
- 3
- 3
- 3
- Unsupervised Trees for Human Action Search3
This chapter proposes a very fast action retrieval system which can effectively locate the subvolumes similar to the query video and proposes a coarse-to-fine subvolume search scheme, which results in a dramatic speedup over the existing video branch-and-bound method.
- 3
- 3
- 3
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 2
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- 1
- Propagative Hough Voting to Leverage Contextual Information1
The superior performances on benchmarked datasets validate that the propagative Hough voting can outperform state-of-the-art techniques in various action analysis tasks, such as action search and recognition.
- Introduction to Human Action Analysis1
This chapter starts from an overview of human action analysis problems, and then discusses the recent development of the four humanaction analysis applications as well as tree-based approaches.
- Human Action Prediction with Multiclass Balanced Random Forest1
This chapter develops a spatial-temporal implicit shape model (STISM), which characterizes the space-time structure of the sparse local features extracted from a video, and proposes a new random forest structure, called multiclass balanced random forest, which makes a good trade-off between the balance of the trees and the discriminative abilities.
- 1
- 1
- 1
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- –
- Supervised Trees for Human Action Recognition and Detection–
In this chapter, a random forest is constructed to efficiently generate discriminative votes from individual interest points, and a fast top-K subvolume search algorithm is developed to find all action instances in a single round of search.
- –
- –
- Research on Pedestrian’s Detection Based on the Integration of AdaBoost Algorithm and Shape Features–
- –
- –
- –
- –
- –
- –
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.