Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks79 from public data
- FCOS: Fully Convolutional One-Stage Object Detection6,481
For the first time, a much simpler and flexible detection framework achieving improved detection accuracy is demonstrated, and it is hoped that the proposed FCOS framework can serve as a simple and strong alternative for many other instance-level tasks.
- Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling1,813
This work explores the relationship between model scaling and performance, systematically exploring the performance trends in vision encoders, language models, dataset sizes, and test-time configurations and hopes this model contributes to the open-source community by setting new standards for developing and applying multimodal AI systems.
- ResNeSt: Split-Attention Networks1,789
This work designs a new variant of the ResNet model, named ResNeSt, which outperforms EfficientNet in terms of the accuracy/latency trade-off and applies channel-wise attention across different network branches to leverage the complementary strengths of both feature-map attention and multi-path representation.
- Bag of Tricks for Image Classification with Convolutional Neural Networks1,654
This paper examines a collection of training procedure refinements and empirically evaluates their impact on the final model accuracy through ablation study, and shows that by combining these refinements together, they are able to improve various CNN models significantly.
- Detecting Text in Natural Image with Connectionist Text Proposal Network1,104
A novel Connectionist Text Proposal Network (CTPN) that accurately localizes text lines in natural image and develops a vertical anchor mechanism that jointly predicts location and text/non-text score of each fixed-width proposal, considerably improving localization accuracy.
- FCOS: A Simple and Strong Anchor-free Object Detector1,044
A fully convolutional one-stage object detector (FCOS) to solve object detection in a per-pixel prediction fashion, analogue to other dense prediction problems such as semantic segmentation, achieving improved detection accuracy.
- 693
- ABCNet: Real-Time Scene Text Spotting With Adaptive Bezier-Curve Network462
For the first time, a novel BezierAlign layer is designed for extracting accurate convolution features of a text instance with arbitrary shapes, significantly improving the precision compared with previous methods and introducing negligible computation overhead.
- Text-Attentional Convolutional Neural Network for Scene Text Detection362
A new system for scene text detection by proposing a novel text-attentional convolutional neural network (Text-CNN) that particularly focuses on extracting text-related regions and features from the image components and a powerful low-level detector called contrast-enhancement maximally stable extremal regions (MSERs) is developed.
- Single Shot Text Detector with Regional Attention336
A novel single-shot text detector that directly outputs word-level bounding boxes in a natural image and develops a hierarchical inception module which efficiently aggregates multi-scale inception features.
- 268
- Decoders Matter for Semantic Segmentation: Data-Dependent Decoding Enables Flexible Feature Aggregation264
This work proposes a data-dependent upsampling (DUpsampling) to replace bilinear, which takes advantages of the redundancy in the label space of semantic segmentation and is able to recover the pixel-wise prediction from low-resolution outputs of CNNs.
- Knowledge Adaptation for Efficient Semantic Segmentation253
This work proposes a knowledge distillation method tailored for semantic segmentation to improve the performance of the compact FCNs with large overall stride and optimize the feature similarity in a transferred latent domain formulated by utilizing a pre-trained autoencoder.
- An End-to-End TextSpotter with Explicit Alignment and Attention244
A novel text-alignment layer is proposed that allows it to precisely compute convolutional features of a text instance in arbitrary orientation, which is the key to boost the performance of the model on the ICDAR 2015.
- ARCH++: Animation-Ready Clothed Human Reconstruction Revisited243
This paper introduces an end-to-end point based geometry encoder to better describe the semantics of the underlying 3D human body, in replacement of previous hand-crafted features, and proposes a co-supervising framework with cross-space consistency to jointly estimate the occupancy in both the posed and canonical spaces.
- 206
- ABCNet v2: Adaptive Bezier-Curve Network for Real-time End-to-end Text Spotting189
This work adaptively fit arbitrarily-shaped text by a parameterized Bezier curve, which, compared with segmentation-based methods, can not only provide structured output but also controllable representation, which can be valuable for real-time applications.
- 145
- Mono3D++: Monocular 3D Vehicle Detection with Two-Scale 3D Hypotheses and Task Priors137
The method to infer 3D pose and shape of vehicles from a single image is presented, using a morphable wireframe model to generate a fine-scaled representation of vehicle shape and pose and jointly model the 3D bounding box as a coarse representation which improves robustness.
- DyCo3D: Robust Instance Segmentation of 3D Point Clouds through Dynamic Convolution133
A dynamic, proposal-free, data-driven approach that generates the appropriate convolution kernels to apply in response to the nature of the instances, which achieves promising results on both ScanetNetV2 and S3DIS, and improves inference speed by more than 25% over the current state-of-the-art.
- 116
- 110
- 92
- 83
- HCRF-Flow: Scene Flow from Point Clouds with Continuous High-order CRFs and Position-aware Flow Embedding63
A high-order CRFs based relation module (Con-HCRFs) is deployed to explore both point-wise smoothness and region-wise rigidity, and a position-aware flow estimation module is introduced to empower the CRFs to have a discriminative unary term.
- OmniWorld: A Multi-Domain and Multi-Modal Dataset for 4D World Modeling59
OmniWorld is introduced, a large-scale, multi-domain, multi-modal dataset specifically designed for 4D world modeling that serves as a catalyst for accelerating the development of general-purpose 4D world models, ultimately advancing machines'holistic understanding of the physical world.
- Coarse-to-Fine Amodal Segmentation with Shape Prior50
A novel approach, called Coarse-to-Fine Segmentation (C2F-Seg), that addresses this problem by progressively modeling the amodal segmentation by introducing a convolution refine module to inject fine-grained information and provide a more precise amodal object segmentation based on visual features and coarse-predicted segmentation.
- 49
- Learning and Memorizing Representative Prototypes for 3D Point Cloud Semantic and Instance Segmentation48
This paper proposes a memory-augmented network to learn and memorize the representative prototypes that cover diverse samples universally, and introduces a memory module to alleviate the forgetting issue by recording the patterns seen in mini-batch training.
- GeoNet: Deep Geodesic Networks for Point Cloud Analysis48
This work introduces GeoNet, the first deep learning architecture trained to model the intrinsic structure of surfaces represented as point clouds, and proposes fusion schemes which use GeoNet in conjunction with other baseline or backbone networks, such as PU-Net and PointNet++, for down-stream point cloud analysis.
- Reconstructing Hand-Held Objects from Monocular Video44
An implicit neural representation-based method is devised to solve the reconstruction problem and address the issues of imprecise hand pose estimation, relative hand-object motion, and insufficient geometry optimization for small objects.
- Learning Hierarchical Graph Neural Networks for Image Clustering44
This work proposes a hierarchical graph neural network model that learns how to cluster a set of images into an unknown number of identities using a training set of image annotated with labels belonging to a disjoint set of identities.
- Adaptive Slot Attention: Object Discovery with Dynamic Slot Number38
An adaptive slot attention (AdaSlot) mecha-nism that dynamically determines the optimal number of slots based on the content of the data is introduced that exhibits the capability to dynamically adapt the slot number according to each instance's complexity.
- 34
- Exploring the Capacity of an Orderless Box Discretization Network for Multi-orientation Scene Text Detection32
A new method, Orderless Box Discretization (OBD), which first discretizes the quadrilateral box into several key edges containing all potential horizontal and vertical positions is proposed, which solves the ambiguity issue and achieves state-of-the-art performance on various benchmarks, including ICDAR 2015 and MLT.
- 31
- 30
- Rough graph and its structure28
Rough graph extends the results of classical graph theory and is the graph that can be used to research uncertainty problems, and is also a new research tool to analyze the system rough characteristic.
- GIF2Video: Color Dequantization and Temporal Interpolation of GIF Images26
This paper proposes GIF2Video, the first learning-based method for enhancing the visual quality of GIFs in the wild by recovering information lost in the three steps of GIF creation: frame sampling, color quantization, and color dithering.
- 24
- DreamComposer: Controllable 3D Object Generation via Multi-View Conditions22
Experiments show that DreamComposer is compatible with state-of-the-art diffusion models for zero-shot novel view synthesis, further enhancing them to generate high-fidelity novel view images with multi-view conditions, ready for controllable 3D object reconstruction and various other applications.
- 22
- Instance-Aware Embedding for Point Cloud Instance Segmentation22
This work proposes an Instance-Aware Module (IAM) that learns discriminative instance embedding features in twofold and is free from complicated and time-consuming operations, showing superiority in both accuracy and efficiency over the previous methods.
- 21
- 18
- Adapter-X: A Novel General Parameter-Efficient Fine-Tuning Framework for Vision17
The proposed Adapter-X is the first to outperform full fine-tuning in both 2D image and 3D point cloud modalities with significantly fewer parameters, i.e., only 0.20% and 1.88% of original trainable parameters for 2D and 3D classification tasks.
- Shape Recovery of Endoscopic Videos by Shape from Shading Using Mesh Regularization17
This work proposes a mesh regularization for shape recovery based on cues derived from Shape-from-Shading (SfS), which can well approximate the underlying non-rigid surfaces, rendering temporally-stabilized meshes for 3D video display.
- MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency16
A novel informative-preserved reconstruction is proposed, which explores local statistics to discover and preserve the representative structured points, effectively enhancing the pretext masking task for 3D scene understanding.
- 16
- 15
- Object-Centric Multiple Object Tracking15
This paper proposes a video object-centric model for MOT that consists of an index-merge module that adapts the object-centric slots into detection outputs and an object memory module that builds complete object prototypes to handle occlusions.
- Unsupervised Open-Vocabulary Object Localization in Videos15
A method that first localizes objects in videos via a slot attention approach and then assigns text to the obtained slots is proposed, which is effectively the first unsupervised approach that yields good results on regular video benchmarks.
- 14
- 13
- 13
- 12
- Rethinking Amodal Video Segmentation from Learning Supervised Signals with Object-centric Representation10
This paper proposes an Efficient object-centric Representation amodal Segmentation (EoRaS), and designs a translation module to project image features into the Bird’s-Eye View (BEV), which introduces 3D information to improve current feature quality.
- Advances in 3D pre-training and downstream tasks: a survey9
This paper provides a comprehensive survey of recent advances in the 3D feld, which encompasses a wide collection of topics, including diverse pre-training strategies, backbone designs and downstream tasks.
- Bag of Tricks for Multimodal AutoML with Image, Text, and Tabular Data9
This study delves into classification and regression problems involving flexible combinations of image, text, and tabular data, and curates a benchmark comprising 22 multimodal datasets from diverse real-world applications, encompassing all 4 combinations of the 3 modalities.
- PSS: Progressive Sample Selection for Open-World Visual Representation Learning8
Experiments demonstrate that the proposed method consistently outperforms state-of-the-art open-world semi-supervised learning methods and novel class discovery methods over nature species image retrieval and face verification benchmarks.
- Single Shot TextSpotter with Explicit Alignment and Attention7
A novel text-alignment layer is proposed that allows it to precisely compute convolutional features of a text instance in ar- bitrary orientation, which is critical to identify challenging text instances.
- 7
- 6
- Learning Primitive Embodied World Models: Towards Scalable Robotic Learning5
This framework leverages the spatiotemporal vision priors in video models and the semantic awareness of VLMs to bridge the gap between fine-grained physical interaction and high-level reasoning, paving the way toward scalable, interpretable, and general-purpose embodied intelligence.
- Exploring the Capacity of Sequential-free Box Discretization Network for Omnidirectional Scene Text Detection.5
The proposed Sequential-free Box Discretization (SBD) departs from the learning ambiguity which has a significant influence during the learning process, and achieves state-of-the-art performance on various benchmarks, including ICDAR 2015, and MLT.
- Sparse Autoencoders, Again?4
Underappreciated weaknesses with both canonical SAEs as well as analogous VAEs applied to similar tasks are formalized, and a hybrid alternative model is proposed that circumvents these prior limitations and is able to exceed the performance of equivalent-capacity SAEs and VAEs.
- BloomGML: Graph Machine Learning through the Lens of Bilevel Optimization4
This paper derives a more flexible class of energy functions that, when paired with various descent steps, form graph neural network message-passing layers that, when paired with various descent steps, form graph neural network (GNN) message-passing layers.
- 3
- 3
- Learning for Transductive Threshold Calibration in Open-World Recognition2
OpenGCN, a Graph Neural Network-based transductive threshold calibration method with enhanced adaptability and robustness, is introduced, allowing for transductive inference of the distance thresholds which also incorporates test-time information.
- 2
- 1
- 1
- 1
- BRIDGE -- Building Reinforcement-Learning Depth-to-Image Data Generation Engine for Monocular Depth Estimation–
BRIDGE, an RL-optimized depth-to-image (D2I) generation framework that synthesizes over 20M realistic and geometrically accurate RGB images, each intrinsically paired with its ground truth depth, from diverse source depth maps, thereby fostering general and robust depth features.
- Tra-MoE: Learning Trajectory Prediction Model from Multiple Domains for Adaptive Policy Conditioning–
- –
- –
- Orientation-Aware Text Proposals Network for Scene Text Detection–
The OA-TPN is able to accurately localize arbitrary-oriented text lines in a natural image and works reliably on multi-scale and multi-orientation text with single-scale images.
Publication data from OpenAlex; citation counts are the higher of OpenAlex and Semantic Scholar, last synced 2026-10-12. 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.