Search Results for author:
Found 162 papers, 77 papers with code
AudCast: Audio-Driven Human Video Generation by Cascaded Diffusion Transformers
Despite the recent progress of audio-driven video generation, existing methods mostly focus on driving facial movements, leading to non-coherent head and body dynamics.
Re-HOLD: Video Hand Object Interaction Reenactment via adaptive Layout-instructed Diffusion Model
Current digital human studies focusing on lip-syncing and body movement are no longer sufficient to meet the growing industrial demand, while human video generation techniques that support interacting with real-world environments (e. g., objects) have not been well investigated.
Interpretable Face Anti-Spoofing: Enhancing Generalization with Multimodal Large Language Models
Face Anti-Spoofing (FAS) is essential for ensuring the security and reliability of facial recognition systems.
Explanatory Instructions: Towards Unified Vision Tasks Understanding and Zero-shot Generalization
In this paper, we explore the idea that CV adopts discrete and terminological task definitions (\eg, ``image segmentation''), which may be a key barrier to zero-shot task generalization.
ALoRE: Efficient Visual Adaptation via Aggregating Low Rank Experts
Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks.
Splatter-360: Generalizable 360$^{\circ}$ Gaussian Splatting for Wide-baseline Panoramic Images
Wide-baseline panoramic images are frequently used in applications like VR and simulations to minimize capturing labor costs and storage needs.
TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting
Physically Based Rendering (PBR) materials play a crucial role in modern graphics, enabling photorealistic rendering across diverse environment maps.
TopoSD: Topology-Enhanced Lane Segment Perception with SDMap Prior
Recent advances in autonomous driving systems have shifted towards reducing reliance on high-definition maps (HDMaps) due to the huge costs of annotation and maintenance.
R-CoT: Reverse Chain-of-Thought Problem Generation for Geometric Reasoning in Large Multimodal Models
Current geometric data generation approaches, which apply preset templates to generate geometric data or use Large Language Models (LLMs) to rephrase questions and answers (Q&A), unavoidably limit data accuracy and diversity.
TALK-Act: Enhance Textural-Awareness for 2D Speaking Avatar Reenactment with Diffusion Model
We propose a Motion-Enhanced Textural Alignment module to enhance the bond between driving and target signals.
MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
The construction of Vectorized High-Definition (HD) map typically requires capturing both category and geometry information of map elements.
Uni$^2$Det: Unified and Universal Framework for Prompt-Guided Multi-dataset 3D Detection
We present Uni$^2$Det, a brand new framework for unified and universal multi-dataset training on 3D detection, enabling robust performance across diverse domains and generalization to unseen domains.
MonoFormer: One Transformer for Both Diffusion and Autoregression
Most existing multimodality methods use separate backbones for autoregression-based discrete text generation and diffusion-based continuous visual generation, or the same backbone by discretizing the visual data to use autoregression for both text and visual generation.
FullAnno: A Data Engine for Enhancing Image Comprehension of MLLMs
To this end, we devised the FullAnno system, which is a data engine that can generate large-scale, high-quality, and fine-grained image annotations consisting of the category and position of objects, region descriptions, text information, as well as image dense captions.
ReSyncer: Rewiring Style-based Generator for Unified Audio-Visually Synced Facial Performer
Lip-syncing videos with given audio is the foundation for various applications including the creation of virtual presenters or performers.
Add-SD: Rational Generation without Manual Reference
Our work contributes in three aspects: proposing a dataset containing numerous instructed image pairs; fine-tuning a diffusion model for rational generation; and generating synthetic data to boost downstream tasks.
LaMI-DETR: Open-Vocabulary Detection with Language Model Instruction
Existing methods enhance open-vocabulary object detection by leveraging the robust open-vocabulary recognition capabilities of Vision-Language Models (VLMs), such as CLIP. However, two main challenges emerge:(1) A deficiency in concept representation, where the category names in CLIP's text space lack textual and visual knowledge.
Ranked #1 on
Open Vocabulary Object Detection
on LVIS v1.0
OPEN: Object-wise Position Embedding for Multi-view 3D Object Detection
Accurate depth information is crucial for enhancing the performance of multi-view 3D object detection.
OVLW-DETR: Open-Vocabulary Light-Weighted Detection Transformer
Open-vocabulary object detection focusing on detecting novel categories guided by natural language.
XLD: A Cross-Lane Dataset for Benchmarking Novel Driving View Synthesis
To address this, this paper presents a synthetic dataset for novel driving view synthesis evaluation, which is specifically designed for autonomous driving simulations.
VDG: Vision-Only Dynamic Gaussian for Driving Simulation
Dynamic Gaussian splatting has led to impressive scene reconstruction and image synthesis advances in novel views.
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.
LW-DETR: A Transformer Replacement to YOLO for Real-Time Detection
In this paper, we present a light-weight detection transformer, LW-DETR, which outperforms YOLOs for real-time object detection.
OpenGaussian: Towards Point-Level 3D Gaussian-based Open Vocabulary Understanding
To ensure robust feature presentation and 3D point-level understanding, we first employ SAM masks without cross-frame associations to train instance features with 3D consistency.
StrucTexTv3: An Efficient Vision-Language Model for Text-rich Image Perception, Comprehension, and Beyond
Text-rich images have significant and extensive value, deeply integrated into various aspects of human life.
Towards Unified Multi-granularity Text Detection with Interactive Attention
Existing OCR engines or document image analysis systems typically rely on training separate models for text detection in varying scenarios and granularities, leading to significant computational complexity and resource demands.
Document Layout Analysis
Optical Character Recognition (OCR)
+3
Decoupled Pseudo-labeling for Semi-Supervised Monocular 3D Object Detection
Additionally, we present a DepthGradient Projection (DGP) module to mitigate optimization conflicts caused by noisy depth supervision of pseudo-labels, effectively decoupling the depth gradient and removing conflicting gradients.
TexRO: Generating Delicate Textures of 3D Models by Recursive Optimization
We propose an optimal viewpoint selection strategy, that finds the most miniature set of viewpoints covering all the faces of a mesh.
Gradient-based Sampling for Class Imbalanced Semi-supervised Object Detection
To tackle the confirmation bias from incorrect pseudo labels of minority classes, the class-rebalancing sampling module resamples unlabeled data following the guidance of the gradient-based reweighting module.
GGRt: Towards Pose-free Generalizable 3D Gaussian Splatting in Real-time
Specifically, we design a novel joint learning framework that consists of an Iterative Pose Optimization Network (IPO-Net) and a Generalizable 3D-Gaussians (G-3DG) model.
VRP-SAM: SAM with Visual Reference Prompt
In this paper, we propose a novel Visual Reference Prompt (VRP) encoder that empowers the Segment Anything Model (SAM) to utilize annotated reference images as prompts for segmentation, creating the VRP-SAM model.
GVA: Reconstructing Vivid 3D Gaussian Avatars from Monocular Videos
In this paper, we present a novel method that facilitates the creation of vivid 3D Gaussian avatars from monocular video inputs (GVA).
KD-DETR: Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling
Based on this observation we propose the first general knowledge distillation paradigm for DETR(KD-DETR) with consistent distillation points sampling for both homogeneous and heterogeneous distillation.
TexOct: Generating Textures of 3D Models with Octree-based Diffusion
This model gradually reduces the texture noise on the octree nodes resulting in the restoration of fine texture.
GIR: 3D Gaussian Inverse Rendering for Relightable Scene Factorization
Our method achieves state-of-the-art performance in both relighting and novel view synthesis tasks among the recently proposed inverse rendering methods while achieving real-time rendering.
HAP: Structure-Aware Masked Image Modeling for Human-Centric Perception
To further capture human characteristics, we propose a structure-invariant alignment loss that enforces different masked views, guided by the human part prior, to be closely aligned for the same image.
Accelerating Vision Transformers Based on Heterogeneous Attention Patterns
On one hand, different images share more similar attention patterns in early layers than later layers, indicating that the dynamic query-by-key self-attention matrix may be replaced with a static self-attention matrix in early layers.
Forward Flow for Novel View Synthesis of Dynamic Scenes
This paper proposes a neural radiance field (NeRF) approach for novel view synthesis of dynamic scenes using forward warping.
VideoGen: A Reference-Guided Latent Diffusion Approach for High Definition Text-to-Video Generation
In this paper, we present VideoGen, a text-to-video generation approach, which can generate a high-definition video with high frame fidelity and strong temporal consistency using reference-guided latent diffusion.
Group Pose: A Simple Baseline for End-to-End Multi-person Pose Estimation
State-of-the-art solutions adopt the DETR-like framework, and mainly develop the complex decoder, e. g., regarding pose estimation as keypoint box detection and combining with human detection in ED-Pose, hierarchically predicting with pose decoder and joint (keypoint) decoder in PETR.
HD-Fusion: Detailed Text-to-3D Generation Leveraging Multiple Noise Estimation
In this paper, we study Text-to-3D content generation leveraging 2D diffusion priors to enhance the quality and detail of the generated 3D models.
Semi-DETR: Semi-Supervised Object Detection with Detection Transformers
Specifically, we propose a Stage-wise Hybrid Matching strategy that combines the one-to-many assignment and one-to-one assignment strategies to improve the training efficiency of the first stage and thus provide high-quality pseudo labels for the training of the second stage.
Learning Structure-Guided Diffusion Model for 2D Human Pose Estimation
One of the mainstream schemes for 2D human pose estimation (HPE) is learning keypoints heatmaps by a neural network.
ICDAR 2023 Competition on Structured Text Extraction from Visually-Rich Document Images
It is hoped that this competition will attract many researchers in the field of CV and NLP, and bring some new thoughts to the field of Document AI.
Building an Invisible Shield for Your Portrait against Deepfakes
Unlike authentic images, where the hidden messages can be extracted with precision, manipulating the facial attributes through deepfake techniques can disrupt the decoding process.
Multi-Modal 3D Object Detection by Box Matching
Extensive experiments on the nuScenes dataset demonstrate that our method is much more stable in dealing with challenging cases such as asynchronous sensors, misaligned sensor placement, and degenerated camera images than existing fusion methods.
Ranked #48 on
3D Object Detection
on nuScenes
StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-based Generator
Despite recent advances in syncing lip movements with any audio waves, current methods still struggle to balance generation quality and the model's generalization ability.
ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Box
We propose a hierarchical data association strategy to mine the true objects in low-score detection boxes, which alleviates the problems of object missing and fragmented trajectories.
Ambiguity-Resistant Semi-Supervised Learning for Dense Object Detection
It employs a "divide-and-conquer" strategy and separately exploits positives for the classification and localization task, which is more robust to the assignment ambiguity.
Ranked #1 on
Semi-Supervised Object Detection
on COCO 10% labeled data
(detector metric)
CAPE: Camera View Position Embedding for Multi-View 3D Object Detection
In this paper, we address the problem of detecting 3D objects from multi-view images.
Ranked #9 on
3D Object Detection
on nuScenes Camera Only
PSVT: End-to-End Multi-person 3D Pose and Shape Estimation with Progressive Video Transformers
To handle the variances of objects as time proceeds, a novel scheme of progressive decoding is used to update pose and shape queries at each frame.
Ranked #32 on
3D Human Pose Estimation
on 3DPW
LMR: A Large-Scale Multi-Reference Dataset for Reference-based Super-Resolution
To this end, we construct a large-scale, multi-reference super-resolution dataset, named LMR.
Delicate Textured Mesh Recovery from NeRF via Adaptive Surface Refinement
Neural Radiance Fields (NeRF) have constituted a remarkable breakthrough in image-based 3D reconstruction.
StrucTexTv2: Masked Visual-Textual Prediction for Document Image Pre-training
Compared to the masked multi-modal modeling methods for document image understanding that rely on both the image and text modalities, StrucTexTv2 models image-only input and potentially deals with more application scenarios free from OCR pre-processing.
Ranked #1 on
Table Recognition
on WTW
Temporal Segment Transformer for Action Segmentation
To deal with these issues, we propose an attention based approach which we call \textit{temporal segment transformer}, for joint segment relation modeling and denoising.
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 #17 on
Skeleton Based Action Recognition
on NTU RGB+D
StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection
In this paper, we propose a cross-modal distillation method named StereoDistill to narrow the gap between the stereo and LiDAR-based approaches via distilling the stereo detectors from the superior LiDAR model at the response level, which is usually overlooked in 3D object detection distillation.
CFCG: Semi-Supervised Semantic Segmentation via Cross-Fusion and Contour Guidance Supervision
Current state-of-the-art semi-supervised semantic segmentation (SSSS) methods typically adopt pseudo labeling and consistency regularization between multiple learners with different perturbations.
Masked Lip-Sync Prediction by Audio-Visual Contextual Exploitation in Transformers
This requires masking a large percentage of the original image and seamlessly inpainting it with the aid of audio and reference frames.
Cyclically Disentangled Feature Translation for Face Anti-spoofing
We further extend CDFTN for multi-target domain adaptation by leveraging data from more unlabeled target domains.
CAE v2: Context Autoencoder with CLIP Target
That is to say, the smaller the model, the lower the mask ratio needs to be.
Knowledge Distillation for Detection Transformer with Consistent Distillation Points Sampling
In this paper, we focus on the compression of DETR with knowledge distillation.
Group DETR v2: Strong Object Detector with Encoder-Decoder Pretraining
The training process consists of self-supervised pretraining and finetuning a ViT-Huge encoder on ImageNet-1K, pretraining the detector on Object365, and finally finetuning it on COCO.
Ranked #7 on
Object Detection
on COCO test-dev
U-HRNet: Delving into Improving Semantic Representation of High Resolution Network for Dense Prediction
Therefore, we designed a U-shaped High-Resolution Network (U-HRNet), which adds more stages after the feature map with strongest semantic representation and relaxes the constraint in HRNet that all resolutions need to be calculated parallel for a newly added stage.
RTFormer: Efficient Design for Real-Time Semantic Segmentation with Transformer
Recently, transformer-based networks have shown impressive results in semantic segmentation.
Ranked #2 on
Real-Time Semantic Segmentation
on CamVid
Repainting and Imitating Learning for Lane Detection
In this paper, we target at finding an enhanced feature space where the lane features are distinctive while maintaining a similar distribution of lanes in the wild.
StyleSwap: Style-Based Generator Empowers Robust Face Swapping
Our core idea is to leverage a style-based generator to empower high-fidelity and robust face swapping, thus the generator's advantage can be adopted for optimizing identity similarity.
Effective Invertible Arbitrary Image Rescaling
To increase its real world applicability, numerous models have also been proposed to restore SR images with arbitrary scale factors, including asymmetric ones where images are resized to different scales along horizontal and vertical directions.
MAFormer: A Transformer Network with Multi-scale Attention Fusion for Visual Recognition
We develop a simple but effective module to explore the full potential of transformers for visual representation by learning fine-grained and coarse-grained features at a token level and dynamically fusing them.
AGO-Net: Association-Guided 3D Point Cloud Object Detection Network
A feasible method is investigated to construct conceptual scenes without external datasets.
CODER: Coupled Diversity-Sensitive Momentum Contrastive Learning for Image-Text Retrieval
We introduce dynamic dictionaries for both modalities to enlarge the scale of image-text pairs, and diversity-sensitiveness is achieved by adaptive negative pair weighting.
Part-aware Prototypical Graph Network for One-shot Skeleton-based Action Recognition
In this paper, we study the problem of one-shot skeleton-based action recognition, which poses unique challenges in learning transferable representation from base classes to novel classes, particularly for fine-grained actions.
Boosting Video-Text Retrieval with Explicit High-Level Semantics
Video-text retrieval (VTR) is an attractive yet challenging task for multi-modal understanding, which aims to search for relevant video (text) given a query (video).
Group DETR: Fast DETR Training with Group-Wise One-to-Many Assignment
Detection transformer (DETR) relies on one-to-one assignment, assigning one ground-truth object to one prediction, for end-to-end detection without NMS post-processing.
UFO: Unified Feature Optimization
UFO aims to benefit each single task with a large-scale pretraining on all tasks.
Detecting Deepfake by Creating Spatio-Temporal Regularity Disruption
Specifically, by carefully examining the spatial and temporal properties, we propose to disrupt a real video through a Pseudo-fake Generator and create a wide range of pseudo-fake videos for training.
Action Quality Assessment with Temporal Parsing Transformer
Action Quality Assessment(AQA) is important for action understanding and resolving the task poses unique challenges due to subtle visual differences.
Neural Color Operators for Sequential Image Retouching
The neural color operator mimics the behavior of traditional color operators and learns pixelwise color transformation while its strength is controlled by a scalar.
Paint and Distill: Boosting 3D Object Detection with Semantic Passing Network
In this work, we propose a novel semantic passing framework, named SPNet, to boost the performance of existing lidar-based 3D detection models with the guidance of rich context painting, with no extra computation cost during inference.
Delving into Sequential Patches for Deepfake Detection
Recent advances in face forgery techniques produce nearly visually untraceable deepfake videos, which could be leveraged with malicious intentions.
Neural Deformable Voxel Grid for Fast Optimization of Dynamic View Synthesis
The second module contains a density and a color grid to model the geometry and density of the scene.
Singular Value Fine-tuning: Few-shot Segmentation requires Few-parameters Fine-tuning
In this paper, we rethink the paradigm and explore a new regime: {\em fine-tuning a small part of parameters in the backbone}.
Ranked #15 on
Few-Shot Semantic Segmentation
on COCO-20i (1-shot)
MaskOCR: Text Recognition with Masked Encoder-Decoder Pretraining
Specifically, we transform text data into synthesized text images to unify the data modalities of vision and language, and enhance the language modeling capability of the sequence decoder using a proposed masked image-language modeling scheme.
Few-Shot Font Generation by Learning Fine-Grained Local Styles
Instead of explicitly disentangling global or component-wise modeling, the cross-attention mechanism can attend to the right local styles in the reference glyphs and aggregate the reference styles into a fine-grained style representation for the given content glyphs.
Few-Shot Head Swapping in the Wild
Particularly, seamless blending is achieved with the help of a Semantic-Guided Color Reference Creation procedure and a Blending UNet.
Human-Object Interaction Detection via Disentangled Transformer
To associate the predictions of disentangled decoders, we first generate a unified representation for HOI triplets with a base decoder, and then utilize it as input feature of each disentangled decoder.
GitNet: Geometric Prior-based Transformation for Birds-Eye-View Segmentation
Birds-eye-view (BEV) semantic segmentation is critical for autonomous driving for its powerful spatial representation ability.
Implicit Sample Extension for Unsupervised Person Re-Identification
Specifically, we generate support samples from actual samples and their neighbouring clusters in the embedding space through a progressive linear interpolation (PLI) strategy.
ViSTA: Vision and Scene Text Aggregation for Cross-Modal Retrieval
Visual appearance is considered to be the most important cue to understand images for cross-modal retrieval, while sometimes the scene text appearing in images can provide valuable information to understand the visual semantics.
Ranked #10 on
Cross-Modal Retrieval
on Flickr30k
(using extra training data)
Rope3D: TheRoadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
On the other hand, the data captured from roadside cameras have strengths over frontal-view data, which is believed to facilitate a safer and more intelligent autonomous driving system.
Adversarial Dual-Student with Differentiable Spatial Warping for Semi-Supervised Semantic Segmentation
The perturbations for unlabeled data enable the consistency training loss, which benefits semi-supervised semantic segmentation.
Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence
Deep learning based single image super-resolution models have been widely studied and superb results are achieved in upscaling low-resolution images with fixed scale factor and downscaling degradation kernel.
MobileFaceSwap: A Lightweight Framework for Video Face Swapping
In this work, we propose a lightweight Identity-aware Dynamic Network (IDN) for subject-agnostic face swapping by dynamically adjusting the model parameters according to the identity information.
Expressive Talking Head Generation With Granular Audio-Visual Control
Generating expressive talking heads is essential for creating virtual humans.
Rope3D: The Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task
On the other hand, the data captured from roadside cameras have strengths over frontal-view data, which is believed to facilitate a safer and more intelligent autonomous driving system.
The Devil is in the Task: Exploiting Reciprocal Appearance-Localization Features for Monocular 3D Object Detection
Low-cost monocular 3D object detection plays a fundamental role in autonomous driving, whereas its accuracy is still far from satisfactory.
Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model
We propose a novel framework, i. e., Predict, Prevent, and Evaluate (PPE), for disentangled text-driven image manipulation that requires little manual annotation while being applicable to a wide variety of manipulations.
An Information Theory-inspired Strategy for Automatic Network Pruning
This practically limits the application of model compression when the model needs to be deployed on a wide range of devices.
Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition
The task of skeleton-based action recognition remains a core challenge in human-centred scene understanding due to the multiple granularities and large variation in human motion.
Paint Transformer: Feed Forward Neural Painting with Stroke Prediction
Neural painting refers to the procedure of producing a series of strokes for a given image and non-photo-realistically recreating it using neural networks.
Ranked #1 on
Object Detection
on A2D
Weakly-Supervised Spatio-Temporal Anomaly Detection in Surveillance Video
In this paper, we introduce a novel task, referred to as Weakly-Supervised Spatio-Temporal Anomaly Detection (WSSTAD) in surveillance video.
AdaAttN: Revisit Attention Mechanism in Arbitrary Neural Style Transfer
Finally, the content feature is normalized so that they demonstrate the same local feature statistics as the calculated per-point weighted style feature statistics.
Ranked #5 on
Style Transfer
on StyleBench
DOLG: Single-Stage Image Retrieval with Deep Orthogonal Fusion of Local and Global Features
Components orthogonal to the global image representation are then extracted from the local information.
StrucTexT: Structured Text Understanding with Multi-Modal Transformers
Due to the complexity of content and layout in VRDs, structured text understanding has been a challenging task.
Oriented Object Detection with Transformer
Object detection with Transformers (DETR) has achieved a competitive performance over traditional detectors, such as Faster R-CNN.
ASCNet: Self-supervised Video Representation Learning with Appearance-Speed Consistency
Specifically, we propose two tasks to learn the appearance and speed consistency, respectively.
Dual-stream Network for Visual Recognition
Transformers with remarkable global representation capacities achieve competitive results for visual tasks, but fail to consider high-level local pattern information in input images.
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
Probabilistic Ranking-Aware Ensembles for Enhanced Object Detections
This leads to a new problem of confidence discrepancy for the detector ensembles.
PAFNet: An Efficient Anchor-Free Object Detector Guidance
Therefore, a trade-off between effectiveness and efficiency is necessary in practical scenarios.
Ranked #1 on
Object Detection
on COCO test-dev
(Hardware Burden metric)
Image Inpainting by End-to-End Cascaded Refinement with Mask Awareness
Inpainting arbitrary missing regions is challenging because learning valid features for various masked regions is nontrivial.
Ranked #5 on
Image Inpainting
on CelebA-HQ
Unsupervised Multi-Source Domain Adaptation for Person Re-Identification
Although achieving great success, most of them only use limited data from a single-source domain for model pre-training, making the rich labeled data insufficiently exploited.
PGNet: Real-time Arbitrarily-Shaped Text Spotting with Point Gathering Network
With a PG-CTC decoder, we gather high-level character classification vectors from two-dimensional space and decode them into text symbols without NMS and RoI operations involved, which guarantees high efficiency.
Ranked #1 on
Scene Text Detection
on ICDAR 2015
(Accuracy metric)
Drafting and Revision: Laplacian Pyramid Network for Fast High-Quality Artistic Style Transfer
Inspired by the common painting process of drawing a draft and revising the details, we introduce a novel feed-forward method named Laplacian Pyramid Network (LapStyle).
Beyond Self-Supervision: A Simple Yet Effective Network Distillation Alternative to Improve Backbones
Recently, research efforts have been concentrated on revealing how pre-trained model makes a difference in neural network performance.
Student-Teacher Feature Pyramid Matching for Anomaly Detection
Anomaly detection is a challenging task and usually formulated as an one-class learning problem for the unexpectedness of anomalies.
Ranked #36 on
Anomaly Detection
on VisA
FaceController: Controllable Attribute Editing for Face in the Wild
By simply employing some existing and easy-obtainable prior information, our method can control, transfer, and edit diverse attributes of faces in the wild.
Ranked #1 on
Face Swapping
on FaceForensics++
(FID metric)
Revealing the Reciprocal Relations Between Self-Supervised Stereo and Monocular Depth Estimation
Second, we introduce an occlusion-aware distillation (OA Distillation) module, which leverages the predicted depths from StereoNet in non-occluded regions to train our monocular depth estimation network named SingleNet.
EC-DARTS: Inducing Equalized and Consistent Optimization Into DARTS
EC-DARTS decouples different operations based on their categories to optimize the operation weights so that the operation gap between them is shrinked.
Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
We argue that the first phase equals building the k-nearest neighbor graph, while the second phase can be viewed as spreading the message within the graph.
Ranked #1 on
Image Retrieval
on Oxford5k
MVFNet: Multi-View Fusion Network for Efficient Video Recognition
Existing state-of-the-art methods have achieved excellent accuracy regardless of the complexity meanwhile efficient spatiotemporal modeling solutions are slightly inferior in performance.
Ranked #34 on
Action Recognition
on Something-Something V1
Coherent Loss: A Generic Framework for Stable Video Segmentation
Video segmentation approaches are of great importance for numerous vision tasks especially in video manipulation for entertainment.
LID 2020: The Learning from Imperfect Data Challenge Results
The purpose of the Learning from Imperfect Data (LID) workshop is to inspire and facilitate the research in developing novel approaches that would harness the imperfect data and improve the data-efficiency during training.
HS-ResNet: Hierarchical-Split Block on Convolutional Neural Network
Moreover, Hierarchical-Split block is very flexible and efficient, which provides a large space of potential network architectures for different applications.
Discriminative Sounding Objects Localization via Self-supervised Audiovisual Matching
First, we propose to learn robust object representations by aggregating the candidate sound localization results in the single source scenes.
AIM 2020 Challenge on Real Image Super-Resolution: Methods and Results
This paper introduces the real image Super-Resolution (SR) challenge that was part of the Advances in Image Manipulation (AIM) workshop, held in conjunction with ECCV 2020.
Real Image Super Resolution Via Heterogeneous Model Ensemble using GP-NAS
With advancement in deep neural network (DNN), recent state-of-the-art (SOTA) image superresolution (SR) methods have achieved impressive performance using deep residual network with dense skip connections.
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}.
PP-YOLO: An Effective and Efficient Implementation of Object Detector
We mainly try to combine various existing tricks that almost not increase the number of model parameters and FLOPs, to achieve the goal of improving the accuracy of detector as much as possible while ensuring that the speed is almost unchanged.
Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement
In the first stage, heatmap regression network is applied to obtain a rough localization result, and a set of proposal keypoints, called guided points, are sampled.
PointTrack++ for Effective Online Multi-Object Tracking and Segmentation
In this work, we present PointTrack++, an effective on-line framework for MOTS, which remarkably extends our recently proposed PointTrack framework.
Segment as Points for Efficient Online Multi-Object Tracking and Segmentation
The resulting online MOTS framework, named PointTrack, surpasses all the state-of-the-art methods including 3D tracking methods by large margins (5. 4% higher MOTSA and 18 times faster over MOTSFusion) with the near real-time speed (22 FPS).
Multi-Object Tracking
Multi-Object Tracking and Segmentation
+1
Associate-3Ddet: Perceptual-to-Conceptual Association for 3D Point Cloud Object Detection
Object detection from 3D point clouds remains a challenging task, though recent studies pushed the envelope with the deep learning techniques.
Learning Generalized Spoof Cues for Face Anti-spoofing
In this paper, we reformulate FAS in an anomaly detection perspective and propose a residual-learning framework to learn the discriminative live-spoof differences which are defined as the spoof cues.
NTIRE 2020 Challenge on Real Image Denoising: Dataset, Methods and Results
This challenge is based on a newly collected validation and testing image datasets, and hence, named SIDD+.
Towards Accurate Scene Text Recognition with Semantic Reasoning Networks
Scene text image contains two levels of contents: visual texture and semantic information.
ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes.
HAMBox: Delving into Online High-quality Anchors Mining for Detecting Outer Faces
In this paper, we propose an Online High-quality Anchor Mining Strategy (HAMBox), which explicitly helps outer faces compensate with high-quality anchors.
Dynamic Instance Normalization for Arbitrary Style Transfer
Prior normalization methods rely on affine transformations to produce arbitrary image style transfers, of which the parameters are computed in a pre-defined way.
EATEN: Entity-aware Attention for Single Shot Visual Text Extraction
Extracting entity from images is a crucial part of many OCR applications, such as entity recognition of cards, invoices, and receipts.
ACFNet: Attentional Class Feature Network for Semantic Segmentation
Recent works have made great progress in semantic segmentation by exploiting richer context, most of which are designed from a spatial perspective.
Chinese Street View Text: Large-scale Chinese Text Reading with Partially Supervised Learning
Most existing text reading benchmarks make it difficult to evaluate the performance of more advanced deep learning models in large vocabularies due to the limited amount of training data.
ICDAR 2019 Competition on Large-scale Street View Text with Partial Labeling -- RRC-LSVT
Robust text reading from street view images provides valuable information for various applications.
ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT)
This paper reports the ICDAR2019 Robust Reading Challenge on Arbitrary-Shaped Text (RRC-ArT) that consists of three major challenges: i) scene text detection, ii) scene text recognition, and iii) scene text spotting.
Perspective-Guided Convolution Networks for Crowd Counting
In this paper, we propose a novel perspective-guided convolution (PGC) for convolutional neural network (CNN) based crowd counting (i. e. PGCNet), which aims to overcome the dramatic intra-scene scale variations of people due to the perspective effect.
Image Inpainting with Learnable Bidirectional Attention Maps
Most convolutional network (CNN)-based inpainting methods adopt standard convolution to indistinguishably treat valid pixels and holes, making them limited in handling irregular holes and more likely to generate inpainting results with color discrepancy and blurriness.
Ranked #2 on
Image Inpainting
on Paris StreetView
An End-to-end Video Text Detector with Online Tracking
Most existing methods attempt to enhance the performance of video text detection by cooperating with video text tracking, but treat these two tasks separately.
A Single-Shot Arbitrarily-Shaped Text Detector based on Context Attended Multi-Task Learning
Detecting scene text of arbitrary shapes has been a challenging task over the past years.
Ranked #18 on
Scene Text Detection
on ICDAR 2015
Editing Text in the Wild
Specifically, we propose an end-to-end trainable style retention network (SRNet) that consists of three modules: text conversion module, background inpainting module and fusion module.
Ranked #1 on
Image Inpainting
on StreetView
BMN: Boundary-Matching Network for Temporal Action Proposal Generation
To address these difficulties, we introduce the Boundary-Matching (BM) mechanism to evaluate confidence scores of densely distributed proposals, which denote a proposal as a matching pair of starting and ending boundaries and combine all densely distributed BM pairs into the BM confidence map.
Ranked #1 on
Action Recognition
on THUMOS’14
Look More Than Once: An Accurate Detector for Text of Arbitrary Shapes
Previous scene text detection methods have progressed substantially over the past years.
Detecting Text in the Wild with Deep Character Embedding Network
However, text in the wild is usually perspectively distorted or curved, which can not be easily tackled by existing approaches.
TextNet: Irregular Text Reading from Images with an End-to-End Trainable Network
Reading text from images remains challenging due to multi-orientation, perspective distortion and especially the curved nature of irregular text.
Compact Generalized Non-local Network
The non-local module is designed for capturing long-range spatio-temporal dependencies in images and videos.
Fine-grained Video Categorization with Redundancy Reduction Attention
Specifically, it firstly summarizes the video by weight-summing all feature vectors in the feature maps of selected frames with a spatio-temporal soft attention, and then predicts which channels to suppress or to enhance according to this summary with a learned non-linear transform.
Ranked #12 on
Action Recognition
on ActivityNet
Multi-Attention Multi-Class Constraint for Fine-grained Image Recognition
Attention-based learning for fine-grained image recognition remains a challenging task, where most of the existing methods treat each object part in isolation, while neglecting the correlations among them.
Ranked #67 on
Fine-Grained Image Classification
on Stanford Cars
3D Pose Estimation for Fine-Grained Object Categories
The new dataset is available at www. umiacs. umd. edu/~wym/3dpose. html
WordSup: Exploiting Word Annotations for Character based Text Detection
When applied in scene text detection, we are thus able to train a robust character detector by exploiting word annotations in the rich large-scale real scene text datasets, e. g. ICDAR15 and COCO-text.
Ranked #4 on
Scene Text Detection
on ICDAR 2013
Localizing by Describing: Attribute-Guided Attention Localization for Fine-Grained Recognition
By designing a novel reward strategy, we are able to learn to locate regions that are spatially and semantically distinctive with reinforcement learning algorithm.
