Search Results for author:
Found 135 papers, 94 papers with code
Partial Scene Text Retrieval
To address this issue, we propose a Ranking MIL (RankMIL) approach to adaptively filter those noisy samples.
Senna: Bridging Large Vision-Language Models and End-to-End Autonomous Driving
In contrast, Large Vision-Language Models (LVLMs) excel in scene understanding and reasoning.
FasterDiT: Towards Faster Diffusion Transformers Training without Architecture Modification
(3) We develop a new supervision method that further accelerates the training process of DiT.
LCD-Net: A Lightweight Remote Sensing Change Detection Network Combining Feature Fusion and Gating Mechanism
To address these challenges, we propose a Lightweight remote sensing Change Detection Network (LCD-Net in short) that reduces model size and computational cost while maintaining high detection performance.
ControlAR: Controllable Image Generation with Autoregressive Models
Firstly, we explore control encoding for AR models and propose a lightweight control encoder to transform spatial inputs (e. g., canny edges or depth maps) into control tokens.
Dynamic 2D Gaussians: Geometrically accurate radiance fields for dynamic objects
In this paper, we propose a novel representation that can reconstruct accurate meshes from sparse image input, named Dynamic 2D Gaussians (D-2DGS).
PersonViT: Large-scale Self-supervised Vision Transformer for Person Re-Identification
To this end, this article introduces the recently emerged Masked Image Modeling (MIM) self-supervised learning method into person ReID, and effectively extracts high-quality global and local features through large-scale unsupervised pre-training by combining masked image modeling and discriminative contrastive learning, and then conducts supervised fine-tuning training in the person ReID task.
LKCell: Efficient Cell Nuclei Instance Segmentation with Large Convolution Kernels
We evaluate our method on the most challenging benchmark and achieve state-of-the-art results (0. 5080 mPQ) in cell nuclei instance segmentation with only 21. 6% FLOPs compared with the previous leading method.
Ranked #1 on
Panoptic Segmentation
on PanNuke
Visual Text Generation in the Wild
However, it is still challenging to render high-quality text images in real-world scenarios, as three critical criteria should be satisfied: (1) Fidelity: the generated text images should be photo-realistic and the contents are expected to be the same as specified in the given conditions; (2) Reasonability: the regions and contents of the generated text should cohere with the scene; (3) Utility: the generated text images can facilitate related tasks (e. g., text detection and recognition).
Causality-inspired Discriminative Feature Learning in Triple Domains for Gait Recognition
Gait recognition is a biometric technology that distinguishes individuals by their walking patterns.
MoSt-DSA: Modeling Motion and Structural Interactions for Direct Multi-Frame Interpolation in DSA Images
Artificial intelligence has become a crucial tool for medical image analysis.
Segment Any 4D Gaussians
However, there is a dearth of research focusing on segmentation within 4D representations.
Occupancy as Set of Points
Owing to the inherent flexibility of the point-based representation, OSP achieves strong performance compared with existing methods and excels in terms of training and inference adaptability.
EVF-SAM: Early Vision-Language Fusion for Text-Prompted Segment Anything Model
Surprisingly, we observe that: (1) multimodal prompts and (2) vision-language models with early fusion (e. g., BEIT-3) are beneficial for prompting SAM for accurate referring segmentation.
Ranked #2 on
Referring Expression Segmentation
on RefCOCO testA
GaussianDreamerPro: Text to Manipulable 3D Gaussians with Highly Enhanced Quality
The main idea is to bind Gaussians to reasonable geometry, which evolves over the whole generation process.
Skim then Focus: Integrating Contextual and Fine-grained Views for Repetitive Action Counting
The key to action counting is accurately locating each video's repetitive actions.
EVA-X: A Foundation Model for General Chest X-ray Analysis with Self-supervised Learning
The diagnosis and treatment of chest diseases play a crucial role in maintaining human health.
Not All Voxels Are Equal: Hardness-Aware Semantic Scene Completion with Self-Distillation
Furthermore, the voxels in the boundary region are more challenging to differentiate than those in the interior.
TOGS: Gaussian Splatting with Temporal Opacity Offset for Real-Time 4D DSA Rendering
To overcome these limitations, we propose TOGS, a Gaussian splatting method with opacity offset over time, which can effectively improve the rendering quality and speed of 4D DSA.
ViTGaze: Gaze Following with Interaction Features in Vision Transformers
Gaze following aims to interpret human-scene interactions by predicting the person's focal point of gaze.
MIM4D: Masked Modeling with Multi-View Video for Autonomous Driving Representation Learning
Learning robust and scalable visual representations from massive multi-view video data remains a challenge in computer vision and autonomous driving.
WeakSAM: Segment Anything Meets Weakly-supervised Instance-level Recognition
Weakly supervised visual recognition using inexact supervision is a critical yet challenging learning problem.
Image-level Supervised Instance Segmentation
object-detection
+3
VADv2: End-to-End Vectorized Autonomous Driving via Probabilistic Planning
Learning a human-like driving policy from large-scale driving demonstrations is promising, but the uncertainty and non-deterministic nature of planning make it challenging.
YOLO-World: Real-Time Open-Vocabulary Object Detection
The You Only Look Once (YOLO) series of detectors have established themselves as efficient and practical tools.
Ranked #5 on
Zero-Shot Object Detection
on MSCOCO
(using extra training data)
Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model
The results demonstrate that Vim is capable of overcoming the computation & memory constraints on performing Transformer-style understanding for high-resolution images and it has great potential to be the next-generation backbone for vision foundation models.
Fast High Dynamic Range Radiance Fields for Dynamic Scenes
To extend HDR NeRF methods to wider applications, we propose a dynamic HDR NeRF framework, named HDR-HexPlane, which can learn 3D scenes from dynamic 2D images captured with various exposures.
Circuit as Set of Points
In our work, we propose a novel perspective for circuit design by treating circuit components as point clouds and using Transformer-based point cloud perception methods to extract features from the circuit.
Label-efficient Segmentation via Affinity Propagation
In this work, we formulate the affinity modeling as an affinity propagation process, and propose a local and a global pairwise affinity terms to generate accurate soft pseudo labels.
4D Gaussian Splatting for Real-Time Dynamic Scene Rendering
Representing and rendering dynamic scenes has been an important but challenging task.
GaussianDreamer: Fast Generation from Text to 3D Gaussians by Bridging 2D and 3D Diffusion Models
In recent times, the generation of 3D assets from text prompts has shown impressive results.
TiAVox: Time-aware Attenuation Voxels for Sparse-view 4D DSA Reconstruction
Additionally, 2D and 3D DSA imaging results can be generated from the reconstructed 4D DSA images.
Condition-Adaptive Graph Convolution Learning for Skeleton-Based Gait Recognition
Graph convolutional networks have been widely applied in skeleton-based gait recognition.
MapTRv2: An End-to-End Framework for Online Vectorized HD Map Construction
We propose a unified permutation-equivalent modeling approach, \ie, modeling map element as a point set with a group of equivalent permutations, which accurately describes the shape of map element and stabilizes the learning process.
Symphonize 3D Semantic Scene Completion with Contextual Instance Queries
`3D Semantic Scene Completion (SSC) has emerged as a nascent and pivotal undertaking in autonomous driving, aiming to predict voxel occupancy within volumetric scenes.
Ranked #1 on
3D Semantic Scene Completion
on KITTI-360
3D Semantic Scene Completion from a single RGB image
Autonomous Driving
SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depth
By integrating the pseudo-depth method and the DCM strategy into the data association process, we propose a new tracker, called SparseTrack.
Ranked #6 on
Multi-Object Tracking
on MOT20
(using extra training data)
Matte Anything: Interactive Natural Image Matting with Segment Anything Models
In our work, we leverage vision foundation models to enhance the performance of natural image matting.
GaitGS: Temporal Feature Learning in Granularity and Span Dimension for Gait Recognition
Gait recognition, a growing field in biological recognition technology, utilizes distinct walking patterns for accurate individual identification.
A Range-Null Space Decomposition Approach for Fast and Flexible Spectral Compressive Imaging
We present RND-SCI, a novel framework for compressive hyperspectral image (HSI) reconstruction.
LiDAR2Map: In Defense of LiDAR-Based Semantic Map Construction Using Online Camera Distillation
To mitigate the defects caused by lacking semantic cues in LiDAR data, we present an online Camera-to-LiDAR distillation scheme to facilitate the semantic learning from image to point cloud.
VMA: Divide-and-Conquer Vectorized Map Annotation System for Large-Scale Driving Scene
We design a divide-and-conquer annotation scheme to solve the spatial extensibility problem of HD map generation, and abstract map elements with a variety of geometric patterns as unified point sequence representation, which can be extended to most map elements in the driving scene.
Improving Post-Training Quantization on Object Detection with Task Loss-Guided Lp Metric
PTQ optimizes the quantization parameters by different metrics to minimize the perturbation of quantization.
TinyDet: Accurate Small Object Detection in Lightweight Generic Detectors
Small object detection requires the detection head to scan a large number of positions on image feature maps, which is extremely hard for computation- and energy-efficient lightweight generic detectors.
WeakTr: Exploring Plain Vision Transformer for Weakly-supervised Semantic Segmentation
Thus a novel weight-based method is proposed to end-to-end estimate the importance of attention heads, while the self-attention maps are adaptively fused for high-quality CAM results that tend to have more complete objects.
RPTQ: Reorder-based Post-training Quantization for Large Language Models
In this paper, we identify that the challenge in quantizing activations in LLMs arises from varying ranges across channels, rather than solely the presence of outliers.
MobileInst: Video Instance Segmentation on the Mobile
To address those issues, we present MobileInst, a lightweight and mobile-friendly framework for video instance segmentation on mobile devices.
OpenInst: A Simple Query-Based Method for Open-World Instance Segmentation
Fortunately, we have identified two observations that help us achieve the best of both worlds: 1) query-based methods demonstrate superiority over dense proposal-based methods in open-world instance segmentation, and 2) learning localization cues is sufficient for open world instance segmentation.
Generalizable Neural Voxels for Fast Human Radiance Fields
Rendering moving human bodies at free viewpoints only from a monocular video is quite a challenging problem.
Benchmarking the Reliability of Post-training Quantization: a Particular Focus on Worst-case Performance
Post-training quantization (PTQ) is a popular method for compressing deep neural networks (DNNs) without modifying their original architecture or training procedures.
VAD: Vectorized Scene Representation for Efficient Autonomous Driving
In this paper, we propose VAD, an end-to-end vectorized paradigm for autonomous driving, which models the driving scene as a fully vectorized representation.
Ranked #7 on
Bench2Drive
on Bench2Drive
Lane Graph as Path: Continuity-preserving Path-wise Modeling for Online Lane Graph Construction
Motivated by this, we propose to model the lane graph in a novel path-wise manner, which well preserves the continuity of the lane and encodes traffic information for planning.
Understanding Self-Supervised Pretraining with Part-Aware Representation Learning
The study is mainly motivated by that random views, used in contrastive learning, and random masked (visible) patches, used in masked image modeling, are often about object parts.
Graph Contrastive Learning for Skeleton-based Action Recognition
In this paper, we propose a graph contrastive learning framework for skeleton-based action recognition (\textit{SkeletonGCL}) to explore the \textit{global} context across all sequences.
Ranked #13 on
Skeleton Based Action Recognition
on NTU RGB+D
A Simple Adaptive Unfolding Network for Hyperspectral Image Reconstruction
We present a simple, efficient, and scalable unfolding network, SAUNet, to simplify the network design with an adaptive alternate optimization framework for hyperspectral image (HSI) reconstruction.
Query6DoF: Learning Sparse Queries as Implicit Shape Prior for Category-Level 6DoF Pose Estimation
Category-level 6DoF object pose estimation intends to estimate the rotation, translation, and size of unseen objects.
PD-Quant: Post-Training Quantization based on Prediction Difference Metric
It determines the quantization parameters by using the information of differences between network prediction before and after quantization.
Perceive, Interact, Predict: Learning Dynamic and Static Clues for End-to-End Motion Prediction
Motion prediction is highly relevant to the perception of dynamic objects and static map elements in the scenarios of autonomous driving.
Box2Mask: Box-supervised Instance Segmentation via Level-set Evolution
In contrast to fully supervised methods using pixel-wise mask labels, box-supervised instance segmentation takes advantage of simple box annotations, which has recently attracted increasing research attention.
BoxTeacher: Exploring High-Quality Pseudo Labels for Weakly Supervised Instance Segmentation
Most existing methods for weakly supervised instance segmentation focus on designing heuristic losses with priors from bounding boxes.
MapTR: Structured Modeling and Learning for Online Vectorized HD Map Construction
High-definition (HD) map provides abundant and precise environmental information of the driving scene, serving as a fundamental and indispensable component for planning in autonomous driving system.
Ranked #8 on
3D Lane Detection
on OpenLane-V2 val
Robust Multi-Object Tracking by Marginal Inference
To address the problem, we present an efficient approach to compute a marginal probability for each pair of objects in real time.
When Counting Meets HMER: Counting-Aware Network for Handwritten Mathematical Expression Recognition
Recently, most handwritten mathematical expression recognition (HMER) methods adopt the encoder-decoder networks, which directly predict the markup sequences from formula images with the attention mechanism.
Box-supervised Instance Segmentation with Level Set Evolution
A simple mask supervised SOLOv2 model is adapted to predict the instance-aware mask map as the level set for each instance.
Vision-based Uneven BEV Representation Learning with Polar Rasterization and Surface Estimation
In this work, we propose PolarBEV for vision-based uneven BEV representation learning.
Improving Nighttime Driving-Scene Segmentation via Dual Image-adaptive Learnable Filters
With DIAL-Filters, we design both unsupervised and supervised frameworks for nighttime driving-scene segmentation, which can be trained in an end-to-end manner.
Warped Convolutional Networks: Bridge Homography to sl(3) algebra by Group Convolution
In this paper, we propose Warped Convolution Networks (WCN) to effectively learn and represent the homography by SL(3) group and sl(3) algebra with group convolution.
Polar Parametrization for Vision-based Surround-View 3D Detection
Based on Polar Parametrization, we propose a surround-view 3D DEtection TRansformer, named PolarDETR.
Featurized Query R-CNN
The query mechanism introduced in the DETR method is changing the paradigm of object detection and recently there are many query-based methods have obtained strong object detection performance.
Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer
GKT leverages the geometric priors to guide the transformer to focus on discriminative regions and unfolds kernel features to generate BEV representation.
Fast Dynamic Radiance Fields with Time-Aware Neural Voxels
A multi-distance interpolation method is proposed and applied on voxel features to model both small and large motions.
Temporally Efficient Vision Transformer for Video Instance Segmentation
To effectively and efficiently model the crucial temporal information within a video clip, we propose a Temporally Efficient Vision Transformer (TeViT) for video instance segmentation (VIS).
Ranked #37 on
Video Instance Segmentation
on OVIS validation
TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation
Although vision transformers (ViTs) have achieved great success in computer vision, the heavy computational cost hampers their applications to dense prediction tasks such as semantic segmentation on mobile devices.
Multi-scale Context-aware Network with Transformer for Gait Recognition
Although gait recognition has drawn increasing research attention recently, since the silhouette differences are quite subtle in spatial domain, temporal feature representation is crucial for gait recognition.
Ranked #3 on
Gait Recognition
on OUMVLP
Knowledge Mining with Scene Text for Fine-Grained Recognition
Recently, the semantics of scene text has been proven to be essential in fine-grained image classification.
Sparse Instance Activation for Real-Time Instance Segmentation
In this paper, we propose a conceptually novel, efficient, and fully convolutional framework for real-time instance segmentation.
Ranked #7 on
Real-time Instance Segmentation
on MSCOCO
AziNorm: Exploiting the Radial Symmetry of Point Cloud for Azimuth-Normalized 3D Perception
For segmentation, we integrate AziNorm into KPConv.
Image-Adaptive YOLO for Object Detection in Adverse Weather Conditions
Though deep learning-based object detection methods have achieved promising results on the conventional datasets, it is still challenging to locate objects from the low-quality images captured in adverse weather conditions.
Deep Level Set for Box-supervised Instance Segmentation in Aerial Images
Instead of learning the pairwise affinity, the level set method with the carefully designed energy functions treats the object segmentation as curve evolution, which is able to accurately recover the object's boundaries and prevent the interference from the indistinguishable background and similar objects.
NeuSample: Neural Sample Field for Efficient View Synthesis
Neural radiance fields (NeRF) have shown great potentials in representing 3D scenes and synthesizing novel views, but the computational overhead of NeRF at the inference stage is still heavy.
Decoupling Visual-Semantic Feature Learning for Robust Scene Text Recognition
As a result, the learning of semantic features is prone to have a bias on the limited vocabulary of the training set, which is called vocabulary reliance.
ByteTrack: Multi-Object Tracking by Associating Every Detection Box
ByteTrack also achieves state-of-the-art performance on MOT20, HiEve and BDD100K tracking benchmarks.
Ranked #1 on
Multiple Object Tracking
on BDD100K val
YOLOP: You Only Look Once for Panoptic Driving Perception
A panoptic driving perception system is an essential part of autonomous driving.
Ranked #3 on
Drivable Area Detection
on BDD100K val
VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild
We estimate 3D poses from the voxel representation by predicting whether each voxel contains a particular body joint.
Ranked #7 on
3D Multi-Person Pose Estimation
on Campus
Hierarchical Aggregation for 3D Instance Segmentation
Instance segmentation on point clouds is a fundamental task in 3D scene perception.
Ranked #4 on
3D Instance Segmentation
on S3DIS
(mCov metric, using extra
training data)
What Makes for Hierarchical Vision Transformer?
Recent studies indicate that hierarchical Vision Transformer with a macro architecture of interleaved non-overlapped window-based self-attention \& shifted-window operation is able to achieve state-of-the-art performance in various visual recognition tasks, and challenges the ubiquitous convolutional neural networks (CNNs) using densely slid kernels.
Tracking Instances as Queries
Recently, query based deep networks catch lots of attention owing to their end-to-end pipeline and competitive results on several fundamental computer vision tasks, such as object detection, semantic segmentation, and instance segmentation.
You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection
Can Transformer perform 2D object- and region-level recognition from a pure sequence-to-sequence perspective with minimal knowledge about the 2D spatial structure?
Ranked #30 on
Object Detection
on COCO-O
MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens
Transformers have offered a new methodology of designing neural networks for visual recognition.
Dynamic Class Queue for Large Scale Face Recognition In the Wild
Since only a subset of classes is selected for each iteration, the computing requirement is reduced.
Ranked #4 on
Face Recognition
on AgeDB-30
Instances as Queries
The key insight of QueryInst is to leverage the intrinsic one-to-one correspondence in object queries across different stages, as well as one-to-one correspondence between mask RoI features and object queries in the same stage.
Ranked #13 on
Object Detection
on COCO-O
Crossover Learning for Fast Online Video Instance Segmentation
For temporal information modeling in VIS, we present a novel crossover learning scheme that uses the instance feature in the current frame to pixel-wisely localize the same instance in other frames.
Ranked #36 on
Video Instance Segmentation
on OVIS validation
Scene Text Retrieval via Joint Text Detection and Similarity Learning
Such a task is usually realized by matching a query text to the recognized words, outputted by an end-to-end scene text spotter.
Weakly-supervised Instance Segmentation via Class-agnostic Learning with Salient Images
Humans have a strong class-agnostic object segmentation ability and can outline boundaries of unknown objects precisely, which motivates us to propose a box-supervised class-agnostic object segmentation (BoxCaseg) based solution for weakly-supervised instance segmentation.
Ranked #5 on
Box-supervised Instance Segmentation
on COCO test-dev
(using extra training data)
Half-Real Half-Fake Distillation for Class-Incremental Semantic Segmentation
Despite their success for semantic segmentation, convolutional neural networks are ill-equipped for incremental learning, \ie, adapting the original segmentation model as new classes are available but the initial training data is not retained.
Learning to Focus: Cascaded Feature Matching Network for Few-shot Image Recognition
By applying the proposed feature matching block in different layers of the few-shot recognition network, multi-scale information among the compared images can be incorporated into the final cascaded matching feature, which boosts the recognition performance further and generalizes better by learning on relationships.
ResizeMix: Mixing Data with Preserved Object Information and True Labels
Especially, CutMix uses a simple but effective method to improve the classifiers by randomly cropping a patch from one image and pasting it on another image.
EfficientPose: Efficient Human Pose Estimation with Neural Architecture Search
Human pose estimation from image and video is a vital task in many multimedia applications.
Learning Global Structure Consistency for Robust Object Tracking
Unlike many existing trackers that focus on modeling only the target, in this work, we consider the \emph{transient variations of the whole scene}.
Boundary-preserving Mask R-CNN
Besides, it is not surprising to observe that BMask R-CNN obtains more obvious improvement when the evaluation criterion requires better localization (e. g., AP$_{75}$) as shown in Fig. 1.
Deep multi-metric learning for text-independent speaker verification
Text-independent speaker verification is an important artificial intelligence problem that has a wide spectrum of applications, such as criminal investigation, payment certification, and interest-based customer services.
Maximum Entropy Regularization and Chinese Text Recognition
Chinese text recognition is more challenging than Latin text due to the large amount of fine-grained Chinese characters and the great imbalance over classes, which causes a serious overfitting problem.
FNA++: Fast Network Adaptation via Parameter Remapping and Architecture Search
In this paper, we propose a Fast Network Adaptation (FNA++) method, which can adapt both the architecture and parameters of a seed network (e. g. an ImageNet pre-trained network) to become a network with different depths, widths, or kernel sizes via a parameter remapping technique, making it possible to use NAS for segmentation and detection tasks a lot more efficiently.
FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Tracking
Formulating MOT as multi-task learning of object detection and re-ID in a single network is appealing since it allows joint optimization of the two tasks and enjoys high computation efficiency.
Ranked #1 on
Multi-Object Tracking
on 2DMOT15
(using extra training data)
Deep Learning-based Detection for COVID-19 from Chest CT using Weak Label
Our weakly-supervised deep learning model can accurately predict the COVID-19 infectious probability in chest CT volumes without the need for annotating the lesions for training.
AlignSeg: Feature-Aligned Segmentation Networks
Aggregating features in terms of different convolutional blocks or contextual embeddings has been proven to be an effective way to strengthen feature representations for semantic segmentation.
Fast Neural Network Adaptation via Parameter Remapping and Architecture Search
In our experiments, we conduct FNA on MobileNetV2 to obtain new networks for both segmentation and detection that clearly out-perform existing networks designed both manually and by NAS.
Diversity Transfer Network for Few-Shot Learning
The learning problem of the sample generation (i. e., diversity transfer) is solved via minimizing an effective meta-classification loss in a single-stage network, instead of the generative loss in previous works.
Patch Aggregator for Scene Text Script Identification
Script identification in the wild is of great importance in a multi-lingual robust-reading system.
All You Need Is Boundary: Toward Arbitrary-Shaped Text Spotting
Recently, end-to-end text spotting that aims to detect and recognize text from cluttered images simultaneously has received particularly growing interest in computer vision.
Deep High-Resolution Representation Learning for Visual Recognition
High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection.
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric, using extra
training data)
Proposal, Tracking and Segmentation (PTS): A Cascaded Network for Video Object Segmentation
Video object segmentation (VOS) aims at pixel-level object tracking given only the annotations in the first frame.
Ranked #1 on
Visual Object Tracking
on YouTube-VOS 2018
(Jaccard (Seen) metric)
Densely Connected Search Space for More Flexible Neural Architecture Search
We revisit the search space design in most previous NAS methods and find the number and widths of blocks are set manually.
Ranked #91 on
Neural Architecture Search
on ImageNet
High-Resolution Representations for Labeling Pixels and Regions
The proposed approach achieves superior results to existing single-model networks on COCO object detection.
Ranked #7 on
Semantic Segmentation
on LIP val
EAT-NAS: Elastic Architecture Transfer for Accelerating Large-scale Neural Architecture Search
In our implementations, architectures are first searched on a small dataset, e. g., CIFAR-10.
DeepExposure: Learning to Expose Photos with Asynchronously Reinforced Adversarial Learning
Based on these sub-images, a local exposure for each sub-image is automatically learned by virtue of policy network sequentially while the reward of learning is globally designed for striking a balance of overall exposures.
CCNet: Criss-Cross Attention for Semantic Segmentation
Compared with the non-local block, the proposed recurrent criss-cross attention module requires 11x less GPU memory usage.
Ranked #7 on
Semantic Segmentation
on FoodSeg103
(using extra training data)
Weakly Supervised Region Proposal Network and Object Detection
The Convolutional Neural Network (CNN) based region proposal generation method (i. e. region proposal network), trained using bounding box annotations, is an essential component in modern fully supervised object detectors.
Mancs: A Multi-task Attentional Network with Curriculum Sampling for Person Re-identification
We propose a novel deep network called Mancs that solves the person re-identification problem from the following aspects: fully utilizing the attention mechanism for the person misalignment problem and properly sampling for the ranking loss to obtain more stable person representation.
PCL: Proposal Cluster Learning for Weakly Supervised Object Detection
The iterative instance classifier refinement is implemented online using multiple streams in convolutional neural networks, where the first is an MIL network and the others are for instance classifier refinement supervised by the preceding one.
Ranked #1 on
Weakly Supervised Object Detection
on ImageNet
Learning to Update for Object Tracking with Recurrent Meta-learner
Generally, model update is formulated as an online learning problem where a target model is learned over the online training set.
Ranked #1 on
Visual Tracking
on OTB-100
Weakly-Supervised Semantic Segmentation Network With Deep Seeded Region Growing
Inspired by the traditional image segmentation methods of seeded region growing, we propose to train a semantic segmentation network starting from the discriminative regions and progressively increase the pixel-level supervision using by seeded region growing.
Ranked #39 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
(using extra training data)
Object Detection in Videos by High Quality Object Linking
In particular, our method improves results by 8. 8% over the static image detector for fast moving objects.
Auto-Encoder Guided GAN for Chinese Calligraphy Synthesis
In this paper, we investigate the Chinese calligraphy synthesis problem: synthesizing Chinese calligraphy images with specified style from standard font(eg.
Point Linking Network for Object Detection
The deep ConvNets based object detectors mainly focus on regressing the coordinates of bounding box, e. g., Faster-R-CNN, YOLO and SSD.
Deep Patch Learning for Weakly Supervised Object Classification and Discovery
Patch-level image representation is very important for object classification and detection, since it is robust to spatial transformation, scale variation, and cluttered background.
Multiple Instance Detection Network with Online Instance Classifier Refinement
We propose a novel online instance classifier refinement algorithm to integrate MIL and the instance classifier refinement procedure into a single deep network, and train the network end-to-end with only image-level supervision, i. e., without object location information.
Ranked #4 on
Weakly Supervised Object Detection
on ImageNet
TextBoxes: A Fast Text Detector with a Single Deep Neural Network
This paper presents an end-to-end trainable fast scene text detector, named TextBoxes, which detects scene text with both high accuracy and efficiency in a single network forward pass, involving no post-process except for a standard non-maximum suppression.
Revisiting Multiple Instance Neural Networks
We propose a new multiple instance neural network to learn bag representations, which is different from the existing multiple instance neural networks that focus on estimating instance label.
Deep FisherNet for Object Classification
Our proposed FisherNet combines convolutional neural network training and Fisher Vector encoding in a single end-to-end structure.
Multi-Oriented Text Detection with Fully Convolutional Networks
In this paper, we propose a novel approach for text detec- tion in natural images.
Ranked #40 on
Scene Text Detection
on ICDAR 2015
Deep Regression for Face Alignment
In this paper, we present a deep regression approach for face alignment.
Strokelets: A Learned Multi-Scale Representation for Scene Text Recognition
Driven by the wide range of applications, scene text detection and recognition have become active research topics in computer vision.
Fusion with Diffusion for Robust Visual Tracking
A key feature of our approach is that the time complexity of the dif-fusion on the TPG is the same as the diffusion process on each of the original graphs, Moreover, it is not necessary to explicitly construct the TPG in our frame-work.
Maximal Cliques that Satisfy Hard Constraints with Application to Deformable Object Model Learning
We propose a novel inference framework for finding maximal cliques in a weighted graph that satisfy hard constraints.
