Search Results for author:
Found 256 papers, 123 papers with code
TCFormer: Visual Recognition via Token Clustering Transformer
Our dynamic tokens possess two crucial characteristics: (1) Representing image regions with similar semantic meanings using the same vision token, even if those regions are not adjacent, and (2) concentrating on regions with valuable details and represent them using fine tokens.
Parametric Primitive Analysis of CAD Sketches with Vision Transformer
This framework consists of a primitive network and a constraint network, transforming the sketch analysis task into a set prediction problem to enhance the effective handling of primitives and constraints.
FaceCom: Towards High-fidelity 3D Facial Shape Completion via Optimization and Inpainting Guidance
Our method can be used in medical prosthetic fabrication and the registration of deficient scanning data.
Phased Consistency Model
The consistency model (CM) has recently made significant progress in accelerating the generation of diffusion models.
Cached Transformers: Improving Transformers with Differentiable Memory Cache
This work introduces a new Transformer model called Cached Transformer, which uses Gated Recurrent Cached (GRC) attention to extend the self-attention mechanism with a differentiable memory cache of tokens.
DriveMLM: Aligning Multi-Modal Large Language Models with Behavioral Planning States for Autonomous Driving
In this work, we delve into the potential of large language models (LLMs) in autonomous driving (AD).
Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
Many reinforcement learning environments (e. g., Minecraft) provide only sparse rewards that indicate task completion or failure with binary values.
Digital Life Project: Autonomous 3D Characters with Social Intelligence
In this work, we present Digital Life Project, a framework utilizing language as the universal medium to build autonomous 3D characters, who are capable of engaging in social interactions and expressing with articulated body motions, thereby simulating life in a digital environment.
Ranked #2 on
Motion Synthesis
on InterHuman
CoNe: Contrast Your Neighbours for Supervised Image Classification
Moreover, to further boost the performance, we propose ``distributional consistency" as a more informative regularization to enable similar instances to have a similar probability distribution.
PPI-NET: End-to-End Parametric Primitive Inference
In engineering applications, line, circle, arc, and point are collectively referred to as primitives, and they play a crucial role in path planning, simulation analysis, and manufacturing.
FlowFormer: A Transformer Architecture and Its Masked Cost Volume Autoencoding for Optical Flow
This paper introduces a novel transformer-based network architecture, FlowFormer, along with the Masked Cost Volume AutoEncoding (MCVA) for pretraining it to tackle the problem of optical flow estimation.
ADDP: Learning General Representations for Image Recognition and Generation with Alternating Denoising Diffusion Process
In each denoising step, our method first decodes pixels from previous VQ tokens, then generates new VQ tokens from the decoded pixels.
Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory
These agents, equipped with the logic and common sense capabilities of LLMs, can skillfully navigate complex, sparse-reward environments with text-based interactions.
Real-time Controllable Denoising for Image and Video
Controllable image denoising aims to generate clean samples with human perceptual priors and balance sharpness and smoothness.
KBNet: Kernel Basis Network for Image Restoration
In this paper, we propose a kernel basis attention (KBA) module, which introduces learnable kernel bases to model representative image patterns for spatial information aggregation.
Ranked #1 on
Color Image Denoising
on McMaster sigma50
Edge Preserving Implicit Surface Representation of Point Clouds
Among them, the differential Laplican regularizer can effectively alleviate the implicit surface unsmoothness caused by the point cloud quality deteriorates; Meanwhile, in order to reduce the excessive smoothing at the edge regions of implicit suface, we proposed a dynamic edge extract strategy for sampling near the sharp edge of point cloud, which can effectively avoid the Laplacian regularizer from smoothing all regions.
Towards All-in-one Pre-training via Maximizing Multi-modal Mutual Information
It has been proved that combining multiple pre-training strategies and data from various modalities/sources can greatly boost the training of large-scale models.
Ranked #2 on
Object Detection
on COCO test-dev
Uni-Perceiver v2: A Generalist Model for Large-Scale Vision and Vision-Language Tasks
In this paper, we propose Uni-Perceiver v2, which is the first generalist model capable of handling major large-scale vision and vision-language tasks with competitive performance.
InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
Compared to the great progress of large-scale vision transformers (ViTs) in recent years, large-scale models based on convolutional neural networks (CNNs) are still in an early state.
Ranked #1 on
Instance Segmentation
on COCO test-dev
(AP50 metric, using extra
training data)
Demystify Transformers & Convolutions in Modern Image Deep Networks
Our experiments on various tasks and an analysis of inductive bias show a significant performance boost due to advanced network-level and block-level designs, but performance differences persist among different STMs.
Magnetic Resonance Fingerprinting with compressed sensing and distance metric learning
Adaptively learning a distance metric from the undersampled training data can significantly improve the matching accuracy of the query fingerprints.
ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild
We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body and solve the scale variation of different body parts.
Ranked #5 on
2D Human Pose Estimation
on COCO-WholeBody
Learning Degradation Representations for Image Deblurring
With the integration, MSDI-Net can handle various and complicated blurry patterns adaptively.
Ranked #20 on
Image Deblurring
on GoPro
Frozen CLIP Models are Efficient Video Learners
Video recognition has been dominated by the end-to-end learning paradigm -- first initializing a video recognition model with weights of a pretrained image model and then conducting end-to-end training on videos.
Ranked #27 on
Action Classification
on Kinetics-400
(using extra training data)
A Hybrid Complex-valued Neural Network Framework with Applications to Electroencephalogram (EEG)
In this article, we present a new EEG signal classification framework by integrating the complex-valued and real-valued Convolutional Neural Network(CNN) with discrete Fourier transform (DFT).
Pose for Everything: Towards Category-Agnostic Pose Estimation
In this paper, we introduce the task of Category-Agnostic Pose Estimation (CAPE), which aims to create a pose estimation model capable of detecting the pose of any class of object given only a few samples with keypoint definition.
Ranked #1 on
Category-Agnostic Pose Estimation
on MP100
Not All Models Are Equal: Predicting Model Transferability in a Self-challenging Fisher Space
It is challenging because the ground-truth model ranking for each task can only be generated by fine-tuning the pre-trained models on the target dataset, which is brute-force and computationally expensive.
Ranked #2 on
Transferability
on classification benchmark
BIMS-PU: Bi-Directional and Multi-Scale Point Cloud Upsampling
The learning and aggregation of multi-scale features are essential in empowering neural networks to capture the fine-grained geometric details in the point cloud upsampling task.
A Simple Baseline for Video Restoration with Grouped Spatial-temporal Shift
In this study, we propose a simple yet effective framework for video restoration.
Ranked #2 on
Deblurring
on GoPro
(using extra training data)
3D Object Detection for Autonomous Driving: A Comprehensive Survey
Autonomous driving, in recent years, has been receiving increasing attention for its potential to relieve drivers' burdens and improve the safety of driving.
Uni-Perceiver-MoE: Learning Sparse Generalist Models with Conditional MoEs
To mitigate such interference, we introduce the Conditional Mixture-of-Experts (Conditional MoEs) to generalist models.
Siamese Image Modeling for Self-Supervised Vision Representation Learning
Driven by these analysis, we propose Siamese Image Modeling (SiameseIM), which predicts the dense representations of an augmented view, based on another masked view from the same image but with different augmentations.
Efficient Burst Raw Denoising with Variance Stabilization and Multi-frequency Denoising Network
As for each sub-network, we propose an efficient multi-frequency denoising network to remove noise of different frequencies.
Not All Tokens Are Equal: Human-centric Visual Analysis via Token Clustering Transformer
Vision transformers have achieved great successes in many computer vision tasks.
Ranked #7 on
2D Human Pose Estimation
on COCO-WholeBody
Learning a Structured Latent Space for Unsupervised Point Cloud Completion
Specifically, we map a series of related partial point clouds into multiple complete shape and occlusion code pairs and fuse the codes to obtain their representations in the unified latent space.
Point2Seq: Detecting 3D Objects as Sequences
We further propose a lightweight scene-to-sequence decoder that can auto-regressively generate words conditioned on features from a 3D scene as well as cues from the preceding words.
RNNPose: Recurrent 6-DoF Object Pose Refinement with Robust Correspondence Field Estimation and Pose Optimization
The correspondence field estimation and pose refinement are conducted alternatively in each iteration to recover the object poses.
Ranked #1 on
6D Pose Estimation using RGB
on LineMOD
Weak Augmentation Guided Relational Self-Supervised Learning
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations.
Ranked #62 on
Self-Supervised Image Classification
on ImageNet
Robust Self-Supervised LiDAR Odometry via Representative Structure Discovery and 3D Inherent Error Modeling
The correct ego-motion estimation basically relies on the understanding of correspondences between adjacent LiDAR scans.
Learning Semantic Abstraction of Shape via 3D Region of Interest
This is in contrast to current methods, which focus solely on either 3D shape abstraction or semantic analysis.
Dynamic Token Normalization Improves Vision Transformers
It is difficult for Transformers to capture inductive bias such as the positional context in an image with LN.
Uni-Perceiver: Pre-training Unified Architecture for Generic Perception for Zero-shot and Few-shot Tasks
The model is pre-trained on several uni-modal and multi-modal tasks, and evaluated on a variety of downstream tasks, including novel tasks that did not appear in the pre-training stage.
IDR: Self-Supervised Image Denoising via Iterative Data Refinement
To evaluate raw image denoising performance in real-world applications, we build a high-quality raw image dataset SenseNoise-500 that contains 500 real-life scenes.
GreedyNASv2: Greedier Search with a Greedy Path Filter
In this paper, we leverage an explicit path filter to capture the characteristics of paths and directly filter those weak ones, so that the search can be thus implemented on the shrunk space more greedily and efficiently.
INTERN: A New Learning Paradigm Towards General Vision
Enormous waves of technological innovations over the past several years, marked by the advances in AI technologies, are profoundly reshaping the industry and the society.
Weakly Supervised Contrastive Learning
Specifically, our proposed framework is based on two projection heads, one of which will perform the regular instance discrimination task.
Rethinking Noise Synthesis and Modeling in Raw Denoising
However, the real raw image noise is contributed by many noise sources and varies greatly among different sensors.
Ranked #2 on
Image Denoising
on SID SonyA7S2 x100
FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting
On the contrary, the soft composition operates by stitching different patches into a whole feature map where pixels in overlapping regions are summed up.
Ranked #3 on
Video Inpainting
on DAVIS
Voxel-based Network for Shape Completion by Leveraging Edge Generation
Deep learning technique has yielded significant improvements in point cloud completion with the aim of completing missing object shapes from partial inputs.
LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector
Compared with the state-of-the-art stereo detector, our method has improved the 3D detection performance of cars, pedestrians, cyclists by 10. 44%, 5. 69%, 5. 97% mAP respectively on the official KITTI benchmark.
Fast Convergence of DETR with Spatially Modulated Co-Attention
However, DETR suffers from its slow convergence.
ReSSL: Relational Self-Supervised Learning with Weak Augmentation
Self-supervised Learning (SSL) including the mainstream contrastive learning has achieved great success in learning visual representations without data annotations.
Ranked #80 on
Self-Supervised Image Classification
on ImageNet
ViTAS: Vision Transformer Architecture Search
Vision transformers (ViTs) inherited the success of NLP but their structures have not been sufficiently investigated and optimized for visual tasks.
Scalable Transformers for Neural Machine Translation
In this paper, we propose a novel Scalable Transformers, which naturally contains sub-Transformers of different scales and have shared parameters.
ViPNAS: Efficient Video Pose Estimation via Neural Architecture Search
Human pose estimation has achieved significant progress in recent years.
Ranked #23 on
Pose Estimation
on COCO test-dev
Self-distillation with Batch Knowledge Ensembling Improves ImageNet Classification
In this way, our BAKE framework achieves online knowledge ensembling across multiple samples with only a single network.
Pose-Controllable Talking Face Generation by Implicitly Modularized Audio-Visual Representation
While speech content information can be defined by learning the intrinsic synchronization between audio-visual modalities, we identify that a pose code will be complementarily learned in a modulated convolution-based reconstruction framework.
Decoupled Spatial-Temporal Transformer for Video Inpainting
Seamless combination of these two novel designs forms a better spatial-temporal attention scheme and our proposed model achieves better performance than state-of-the-art video inpainting approaches with significant boosted efficiency.
Visually Informed Binaural Audio Generation without Binaural Audios
Moreover, combined with binaural recordings, our method is able to further boost the performance of binaural audio generation under supervised settings.
Semantic Scene Completion via Integrating Instances and Scene in-the-Loop
The key insight is that we decouple the instances from a coarsely completed semantic scene instead of a raw input image to guide the reconstruction of instances and the overall scene.
Ranked #2 on
3D Semantic Scene Completion
on NYUv2
Fixing the Teacher-Student Knowledge Discrepancy in Distillation
To solve this problem, in this paper, we propose a novel student-dependent distillation method, knowledge consistent distillation, which makes teacher's knowledge more consistent with the student and provides the best suitable knowledge to different student networks for distillation.
Learning Fine-Grained Segmentation of 3D Shapes without Part Labels
Learning-based 3D shape segmentation is usually formulated as a semantic labeling problem, assuming that all parts of training shapes are annotated with a given set of tags.
DivCo: Diverse Conditional Image Synthesis via Contrastive Generative Adversarial Network
Conditional generative adversarial networks (cGANs) target at synthesizing diverse images given the input conditions and latent codes, but unfortunately, they usually suffer from the issue of mode collapse.
PV-RCNN++: Point-Voxel Feature Set Abstraction With Local Vector Representation for 3D Object Detection
3D object detection is receiving increasing attention from both industry and academia thanks to its wide applications in various fields.
Ranked #2 on
3D Object Detection
on KITTI Cars Easy val
Fast Convergence of DETR with Spatially Modulated Co-Attention
The recently proposed Detection Transformer (DETR) model successfully applies Transformer to objects detection and achieves comparable performance with two-stage object detection frameworks, such as Faster-RCNN.
Probabilistic Graph Attention Network with Conditional Kernels for Pixel-Wise Prediction
In contrast to previous works directly considering multi-scale feature maps obtained from the inner layers of a primary CNN architecture, and simply fusing the features with weighted averaging or concatenation, we propose a probabilistic graph attention network structure based on a novel Attention-Gated Conditional Random Fields (AG-CRFs) model for learning and fusing multi-scale representations in a principled manner.
STAR: A Structure-Aware Lightweight Transformer for Real-Time Image Enhancement
STAR is a general architecture that can be easily adapted to different image enhancement tasks.
Learning With Privileged Tasks
Concretely, we introduce a privileged parameter so that the optimization direction does not necessarily follow the gradient from the privileged tasks, but concentrates more on the target tasks.
A Holistically-Guided Decoder for Deep Representation Learning with Applications to Semantic Segmentation and Object Detection
With the proposed holistically-guided decoder, we implement the EfficientFCN architecture for semantic segmentation and HGD-FPN for object detection and instance segmentation.
End-to-End Object Detection with Adaptive Clustering Transformer
In this paper, a novel variant of transformer named Adaptive Clustering Transformer(ACT) has been proposed to reduce the computation cost for high-resolution input.
Cascaded Refinement Network for Point Cloud Completion with Self-supervision
This is to mitigate the dependence of existing approaches on large amounts of ground truth training data that are often difficult to obtain in real-world applications.
Auto Seg-Loss: Searching Metric Surrogates for Semantic Segmentation
In this paper, we propose to automate the design of metric-specific loss functions by searching differentiable surrogate losses for each metric.
Deformable DETR: Deformable Transformers for End-to-End Object Detection
DETR has been recently proposed to eliminate the need for many hand-designed components in object detection while demonstrating good performance.
Ranked #8 on
2D Object Detection
on SARDet-100K
Open-Edit: Open-Domain Image Manipulation with Open-Vocabulary Instructions
We propose a novel algorithm, named Open-Edit, which is the first attempt on open-domain image manipulation with open-vocabulary instructions.
Point Cloud Completion by Learning Shape Priors
Then we learn a mapping to transfer the point features from partial points to that of the complete points by optimizing feature alignment losses.
Gradient Regularized Contrastive Learning for Continual Domain Adaptation
At the core of our method, gradient regularization plays two key roles: (1) enforces the gradient of contrastive loss not to increase the supervised training loss on the source domain, which maintains the discriminative power of learned features; (2) regularizes the gradient update on the new domain not to increase the classification loss on the old target domains, which enables the model to adapt to an in-coming target domain while preserving the performance of previously observed domains.
Sep-Stereo: Visually Guided Stereophonic Audio Generation by Associating Source Separation
Stereophonic audio is an indispensable ingredient to enhance human auditory experience.
PIE-NET: Parametric Inference of Point Cloud Edges
We introduce an end-to-end learnable technique to robustly identify feature edges in 3D point cloud data.
3D Human Mesh Regression with Dense Correspondence
This paper proposes a model-free 3D human mesh estimation framework, named DecoMR, which explicitly establishes the dense correspondence between the mesh and the local image features in the UV space (i. e. a 2D space used for texture mapping of 3D mesh).
Ranked #1 on
3D Human Reconstruction
on Surreal
Adaptive Momentum Coefficient for Neural Network Optimization
We propose a novel and efficient momentum-based first-order algorithm for optimizing neural networks which uses an adaptive coefficient for the momentum term.
StereoGAN: Bridging Synthetic-to-Real Domain Gap by Joint Optimization of Domain Translation and Stereo Matching
Large-scale synthetic datasets are beneficial to stereo matching but usually introduce known domain bias.
Cascaded Refinement Network for Point Cloud Completion
Point clouds are often sparse and incomplete.
Rotate-and-Render: Unsupervised Photorealistic Face Rotation from Single-View Images
Though face rotation has achieved rapid progress in recent years, the lack of high-quality paired training data remains a great hurdle for existing methods.
1st Place Solutions for OpenImage2019 -- Object Detection and Instance Segmentation
Given such good instance bounding box, we further design a simple instance-level semantic segmentation pipeline and achieve the 1st place on the segmentation challenge.
Revisiting the Sibling Head in Object Detector
The ``shared head for classification and localization'' (sibling head), firstly denominated in Fast RCNN~\cite{girshick2015fast}, has been leading the fashion of the object detection community in the past five years.
Ranked #79 on
Object Detection
on COCO test-dev
KPNet: Towards Minimal Face Detector
The small receptive field and capacity of minimal neural networks limit their performance when using them to be the backbone of detectors.
Adapting Object Detectors with Conditional Domain Normalization
Then this domain-vector is used to encode the features from another domain through a conditional normalization, resulting in different domains' features carrying the same domain attribute.
Ranked #1 on
Unsupervised Domain Adaptation
on SIM10K to BDD100K
Structured Domain Adaptation with Online Relation Regularization for Unsupervised Person Re-ID
To tackle the challenges, we propose an end-to-end structured domain adaptation framework with an online relation-consistency regularization term.
Ranked #5 on
Unsupervised Domain Adaptation
on Market to MSMT
Channel Equilibrium Networks for Learning Deep Representation
Unlike prior arts that simply removed the inhibited channels, we propose to "wake them up" during training by designing a novel neural building block, termed Channel Equilibrium (CE) block, which enables channels at the same layer to contribute equally to the learned representation.
Monocular 3D Object Detection with Decoupled Structured Polygon Estimation and Height-Guided Depth Estimation
Monocular 3D object detection task aims to predict the 3D bounding boxes of objects based on monocular RGB images.
Single Image Dehazing Using Ranking Convolutional Neural Network
To obtain effective features for single image dehazing, this paper presents a novel Ranking Convolutional Neural Network (Ranking-CNN).
PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds.
Search to Distill: Pearls are Everywhere but not the Eyes
Standard Knowledge Distillation (KD) approaches distill the knowledge of a cumbersome teacher model into the parameters of a student model with a pre-defined architecture.
Vision-Infused Deep Audio Inpainting
Extensive experiments demonstrate that our framework is capable of inpainting realistic and varying audio segments with or without visual contexts.
Learning to Predict Layout-to-image Conditional Convolutions for Semantic Image Synthesis
Semantic image synthesis aims at generating photorealistic images from semantic layouts.
Channel Equilibrium Networks
However, over-sparse CNNs have many collapsed channels (i. e. many channels with undesired zero values), impeding their learning ability.
CAMP: Cross-Modal Adaptive Message Passing for Text-Image Retrieval
Text-image cross-modal retrieval is a challenging task in the field of language and vision.
Ranked #9 on
Image Retrieval
on Flickr30K 1K test
Differentiable Learning-to-Group Channels via Groupable Convolutional Neural Networks
ResNeXt, still suffers from the sub-optimal performance due to manually defining the number of groups as a constant over all of the layers.
Once a MAN: Towards Multi-Target Attack via Learning Multi-Target Adversarial Network Once
Recently, generation-based methods have received much attention since they directly use feed-forward networks to generate the adversarial samples, which avoid the time-consuming iterative attacking procedure in optimization-based and gradient-based methods.
Interpolated Convolutional Networks for 3D Point Cloud Understanding
Our InterpConv is shown to be permutation and sparsity invariant, and can directly handle irregular inputs.
Ranked #28 on
3D Part Segmentation
on ShapeNet-Part
Multi-modality Latent Interaction Network for Visual Question Answering
The proposed module learns the cross-modality relationships between latent visual and language summarizations, which summarize visual regions and question into a small number of latent representations to avoid modeling uninformative individual region-word relations.
Deep Self-Learning From Noisy Labels
Unlike previous works constrained by many conditions, making them infeasible to real noisy cases, this work presents a novel deep self-learning framework to train a robust network on the real noisy datasets without extra supervision.
From Points to Parts: 3D Object Detection from Point Cloud with Part-aware and Part-aggregation Network
3D object detection from LiDAR point cloud is a challenging problem in 3D scene understanding and has many practical applications.
Finding Task-Relevant Features for Few-Shot Learning by Category Traversal
Few-shot learning is an important area of research.
P2SGrad: Refined Gradients for Optimizing Deep Face Models
Cosine-based softmax losses significantly improve the performance of deep face recognition networks.
PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
Therefore, to generate the images with preferred objects and rich interactions, we propose a semi-parametric method, PasteGAN, for generating the image from the scene graph and the image crops, where spatial arrangements of the objects and their pair-wise relationships are defined by the scene graph and the object appearances are determined by the given object crops.
AdaCos: Adaptively Scaling Cosine Logits for Effectively Learning Deep Face Representations
Our results show that training deep neural networks with the AdaCos loss is stable and able to achieve high face recognition accuracy.
Ranked #6 on
Face Verification
on MegaFace
Disentangling Pose from Appearance in Monochrome Hand Images
Hand pose estimation from the monocular 2D image is challenging due to the variation in lighting, appearance, and background.
Conditional Adversarial Generative Flow for Controllable Image Synthesis
Flow-based generative models show great potential in image synthesis due to its reversible pipeline and exact log-likelihood target, yet it suffers from weak ability for conditional image synthesis, especially for multi-label or unaware conditions.
Semantics Disentangling for Text-to-Image Generation
Synthesizing photo-realistic images from text descriptions is a challenging problem.
Context and Attribute Grounded Dense Captioning
Dense captioning aims at simultaneously localizing semantic regions and describing these regions-of-interest (ROIs) with short phrases or sentences in natural language.
Ranked #3 on
Dense Captioning
on Visual Genome
Feature Intertwiner for Object Detection
We argue that the reliable set could guide the feature learning of the less reliable set during training - in spirit of student mimicking teacher behavior and thus pushing towards a more compact class centroid in the feature space.
Ranked #145 on
Object Detection
on COCO test-dev
GS3D: An Efficient 3D Object Detection Framework for Autonomous Driving
We present an efficient 3D object detection framework based on a single RGB image in the scenario of autonomous driving.
Ranked #18 on
Vehicle Pose Estimation
on KITTI Cars Hard
Weakly-Supervised Discovery of Geometry-Aware Representation for 3D Human Pose Estimation
Recent studies have shown remarkable advances in 3D human pose estimation from monocular images, with the help of large-scale in-door 3D datasets and sophisticated network architectures.
Video Generation from Single Semantic Label Map
This paper proposes the novel task of video generation conditioned on a SINGLE semantic label map, which provides a good balance between flexibility and quality in the generation process.
Group-wise Correlation Stereo Network
Previous works built cost volumes with cross-correlation or concatenation of left and right features across all disparity levels, and then a 2D or 3D convolutional neural network is utilized to regress the disparity maps.
Shape2Motion: Joint Analysis of Motion Parts and Attributes from 3D Shapes
For the task of mobility analysis of 3D shapes, we propose joint analysis for simultaneous motion part segmentation and motion attribute estimation, taking a single 3D model as input.
SSN: Learning Sparse Switchable Normalization via SparsestMax
Unlike $\ell_1$ and $\ell_0$ constraints that impose difficulties in optimization, we turn this constrained optimization problem into feed-forward computation by proposing SparsestMax, which is a sparse version of softmax.
Unsupervised Cross-spectral Stereo Matching by Learning to Synthesize
Unsupervised cross-spectral stereo matching aims at recovering disparity given cross-spectral image pairs without any supervision in the form of ground truth disparity or depth.
Improving Referring Expression Grounding with Cross-modal Attention-guided Erasing
Referring expression grounding aims at locating certain objects or persons in an image with a referring expression, where the key challenge is to comprehend and align various types of information from visual and textual domain, such as visual attributes, location and interactions with surrounding regions.
Unsupervised Bi-directional Flow-based Video Generation from one Snapshot
Imagining multiple consecutive frames given one single snapshot is challenging, since it is difficult to simultaneously predict diverse motions from a single image and faithfully generate novel frames without visual distortions.
DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images
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.
Dynamic Fusion with Intra- and Inter- Modality Attention Flow for Visual Question Answering
It can robustly capture the high-level interactions between language and vision domains, thus significantly improves the performance of visual question answering.
PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
In this paper, we propose PointRCNN for 3D object detection from raw point cloud.
Ranked #2 on
Object Detection
on KITTI Cars Moderate
Gradient Harmonized Single-stage Detector
Despite the great success of two-stage detectors, single-stage detector is still a more elegant and efficient way, yet suffers from the two well-known disharmonies during training, i. e. the huge difference in quantity between positive and negative examples as well as between easy and hard examples.
Ranked #176 on
Object Detection
on COCO test-dev
FD-GAN: Pose-guided Feature Distilling GAN for Robust Person Re-identification
Our proposed FD-GAN achieves state-of-the-art performance on three person reID datasets, which demonstrates that the effectiveness and robust feature distilling capability of the proposed FD-GAN.
Ranked #4 on
Person Re-Identification
on CUHK03
Learning to Group and Label Fine-Grained Shape Components
We propose to generate part hypotheses from the components based on a hierarchical grouping strategy, and perform labeling on those part groups instead of directly on the components.
Deep Learning for Generic Object Detection: A Survey
Object detection, one of the most fundamental and challenging problems in computer vision, seeks to locate object instances from a large number of predefined categories in natural images.
HMS-Net: Hierarchical Multi-scale Sparsity-invariant Network for Sparse Depth Completion
Dense depth cues are important and have wide applications in various computer vision tasks.
Ranked #10 on
Depth Completion
on KITTI Depth Completion
Learning Monocular Depth by Distilling Cross-domain Stereo Networks
Monocular depth estimation aims at estimating a pixelwise depth map for a single image, which has wide applications in scene understanding and autonomous driving.
Neural Network Encapsulation
Motivated by the routing to make higher capsule have agreement with lower capsule, we extend the mechanism as a compensation for the rapid loss of information in nearby layers.
Question-Guided Hybrid Convolution for Visual Question Answering
Most state-of-the-art VQA methods fuse the high-level textual and visual features from the neural network and abandon the visual spatial information when learning multi-modal features. To address these problems, question-guided kernels generated from the input question are designed to convolute with visual features for capturing the textual and visual relationship in the early stage.
Ranked #14 on
Visual Question Answering (VQA)
on CLEVR
Improving Deep Visual Representation for Person Re-identification by Global and Local Image-language Association
Person re-identification is an important task that requires learning discriminative visual features for distinguishing different person identities.
Ranked #24 on
Text based Person Retrieval
on CUHK-PEDES
End-to-End Deep Kronecker-Product Matching for Person Re-identification
Person re-identification aims to robustly measure similarities between person images.
Deep Group-shuffling Random Walk for Person Re-identification
Person re-identification aims at finding a person of interest in an image gallery by comparing the probe image of this person with all the gallery images.
Person Re-identification with Deep Similarity-Guided Graph Neural Network
However, existing person re-identification models mostly estimate the similarities of different image pairs of probe and gallery images independently while ignores the relationship information between different probe-gallery pairs.
Ranked #2 on
Person Re-Identification
on CUHK03
Talking Face Generation by Adversarially Disentangled Audio-Visual Representation
Talking face generation aims to synthesize a sequence of face images that correspond to a clip of speech.
SCAN: Self-and-Collaborative Attention Network for Video Person Re-identification
To address the above issues, we present a novel and practical deep architecture for video person re-identification termed Self-and-Collaborative Attention Network (SCAN).
Zoom-Net: Mining Deep Feature Interactions for Visual Relationship Recognition
We show that by encouraging deep message propagation and interactions between local object features and global predicate features, one can achieve compelling performance in recognizing complex relationships without using any linguistic priors.
Factorizable Net: An Efficient Subgraph-based Framework for Scene Graph Generation
Generating scene graph to describe all the relations inside an image gains increasing interests these years.
Ranked #1 on
Scene Graph Generation
on VRD
Deep Continuous Conditional Random Fields with Asymmetric Inter-object Constraints for Online Multi-object Tracking
In addition, inter-object relations are mostly modeled in a symmetric way, which we argue is not an optimal setting.
Eliminating Background-Bias for Robust Person Re-Identification
State-of-the-art methods mainly utilize deep learning based approaches for learning visual features for describing person appearances.
Video Person Re-Identification With Competitive Snippet-Similarity Aggregation and Co-Attentive Snippet Embedding
The attention weights are obtained based on a query feature, which is learned from the whole probe snippet by an LSTM network, making the resulting embeddings less affected by noisy frames.
Ranked #4 on
Person Re-Identification
on PRID2011
FaceID-GAN: Learning a Symmetry Three-Player GAN for Identity-Preserving Face Synthesis
Existing methods typically formulate GAN as a two-player game, where a discriminator distinguishes face images from the real and synthesized domains, while a generator reduces its discriminativeness by synthesizing a face of photo-realistic quality.
Group Consistent Similarity Learning via Deep CRF for Person Re-Identification
Extensive experiments demonstrate the effectiveness of our model that combines DNN and CRF for learning robust multi-scale local similarities.
Lehmer Transform and its Theoretical Properties
We propose a new class of transforms that we call {\it Lehmer Transform} which is motivated by the {\it Lehmer mean function}.
PAD-Net: Multi-Tasks Guided Prediction-and-Distillation Network for Simultaneous Depth Estimation and Scene Parsing
Depth estimation and scene parsing are two particularly important tasks in visual scene understanding.
Ranked #15 on
Depth Estimation
on NYU-Depth V2
Avatar-Net: Multi-scale Zero-shot Style Transfer by Feature Decoration
Zero-shot artistic style transfer is an important image synthesis problem aiming at transferring arbitrary style into content images.
Learnable Histogram: Statistical Context Features for Deep Neural Networks
Statistical features, such as histogram, Bag-of-Words (BoW) and Fisher Vector, were commonly used with hand-crafted features in conventional classification methods, but attract less attention since the popularity of deep learning methods.
Exploring Disentangled Feature Representation Beyond Face Identification
This paper proposes learning disentangled but complementary face features with minimal supervision by face identification.
Diversity Regularized Spatiotemporal Attention for Video-based Person Re-identification
As a result, the network learns latent representations of the face, torso and other body parts using the best available image patches from the entire video sequence.