Search Results for author:
Found 49 papers, 20 papers with code
Edit3K: Universal Representation Learning for Video Editing Components
Each video in our dataset is rendered by various image/video materials with a single editing component, which supports atomic visual understanding of different editing components.
Beyond MOT: Semantic Multi-Object Tracking
Current multi-object tracking (MOT) aims to predict trajectories of targets (i. e.,"where") in videos.
VastTrack: Vast Category Visual Object Tracking
The rich annotations of VastTrack enables development of both the vision-only and the vision-language tracking.
BPDO:Boundary Points Dynamic Optimization for Arbitrary Shape Scene Text Detection
Arbitrary shape scene text detection is of great importance in scene understanding tasks.
Text Region Multiple Information Perception Network for Scene Text Detection
Segmentation-based scene text detection algorithms can handle arbitrary shape scene texts and have strong robustness and adaptability, so it has attracted wide attention.
CMFN: Cross-Modal Fusion Network for Irregular Scene Text Recognition
However, the guidance of visual cues is ignored in the process of semantic mining, which limits the performance of the algorithm in recognizing irregular scene text.
High-Quality Mesh Blendshape Generation from Face Videos via Neural Inverse Rendering
Experiments demonstrate that, with the flexible input of single or sparse multi-view videos, we reconstruct personalized high-fidelity blendshapes.
Context-Guided Spatio-Temporal Video Grounding
The key of CG-STVG lies in two specially designed modules, including instance context generation (ICG), which focuses on discovering visual context information (in both appearance and motion) of the instance, and instance context refinement (ICR), which aims to improve the instance context from ICG by eliminating irrelevant or even harmful information from the context.
Ranked #1 on
Spatio-Temporal Video Grounding
on HC-STVG1
Flow-Guided Diffusion for Video Inpainting
Video inpainting has been challenged by complex scenarios like large movements and low-light conditions.
Local Compressed Video Stream Learning for Generic Event Boundary Detection
Specifically, we use lightweight ConvNets to extract features of the P-frames in the GOPs and spatial-channel attention module (SCAM) is designed to refine the feature representations of the P-frames based on the compressed information with bidirectional information flow.
Accurate and Fast Compressed Video Captioning
Addressing this, we study video captioning from a different perspective in compressed domain, which brings multi-fold advantages over the existing pipeline: 1) Compared to raw images from the decoded video, the compressed video, consisting of I-frames, motion vectors and residuals, is highly distinguishable, which allows us to leverage the entire video for learning without manual sampling through a specialized model design; 2) The captioning model is more efficient in inference as smaller and less redundant information is processed.
Ranked #8 on
Video Captioning
on VATEX
Collaborative Three-Stream Transformers for Video Captioning
Meanwhile, we propose a cross-granularity attention module to align the interactions modeled by the three branches of transformers, then the three branches of transformers can support each other to exploit the most discriminative semantic information of different granularities for accurate predictions of captions.
Unsupervised Domain Adaptive Detection with Network Stability Analysis
In this work, drawing inspiration from the concept of stability from the control theory that a robust system requires to remain consistent both externally and internally regardless of disturbances, we propose a novel framework that achieves unsupervised domain adaptive detection through stability analysis.
AttMOT: Improving Multiple-Object Tracking by Introducing Auxiliary Pedestrian Attributes
To the best of our knowledge, AttMOT is the first MOT dataset with semantic attributes.
Deficiency-Aware Masked Transformer for Video Inpainting
Firstly, we pretrain a image inpainting model DMT_img serve as a prior for distilling the video model DMT_vid, thereby benefiting the hallucination of deficiency cases.
Ranked #1 on
Video Inpainting
on DAVIS
MaGIC: Multi-modality Guided Image Completion
In this paper, we propose a novel, simple yet effective method for Multi-modal Guided Image Completion, dubbed MaGIC, which not only supports a wide range of single modality as the guidance (e. g., text, canny edge, sketch, segmentation, depth, and pose), but also adapts to arbitrarily customized combination of these modalities (i. e., arbitrary multi-modality) for image completion.
Two Birds, One Stone: A Unified Framework for Joint Learning of Image and Video Style Transfers
Current arbitrary style transfer models are limited to either image or video domains.
Text with Knowledge Graph Augmented Transformer for Video Captioning
Meanwhile, the internal stream is designed to exploit the multi-modality information in videos (e. g., the appearance of video frames, speech transcripts, and video captions) to ensure the quality of caption results.
Ranked #7 on
Video Captioning
on YouCook2
PlanarTrack: A Large-scale Challenging Benchmark for Planar Object Tracking
In addition, we further derive a variant named PlanarTrack$_{\mathbf{BB}}$ for generic object tracking from PlanarTrack.
SDF-3DGAN: A 3D Object Generative Method Based on Implicit Signed Distance Function
We apply SDF for higher quality representation of 3D object in space and design a new SDF neural renderer, which has higher efficiency and higher accuracy.
Learning Density-Based Correlated Equilibria for Markov Games
In real-world multi-agent systems, in addition to being in an equilibrium, agents' policies are often expected to meet requirements with respect to safety, and fairness.
Robust Domain Adaptive Object Detection with Unified Multi-Granularity Alignment
To reduce discrepancy in feature distributions between two domains, recent approaches achieve domain adaption through feature alignment in different granularities via adversarial learning.
PIDray: A Large-scale X-ray Benchmark for Real-World Prohibited Item Detection
Automatic security inspection relying on computer vision technology is a challenging task in real-world scenarios due to many factors, such as intra-class variance, class imbalance, and occlusion.
High-Fidelity Image Inpainting with GAN Inversion
Addressing this problem, in this paper, we devise a novel GAN inversion model for image inpainting, dubbed InvertFill, mainly consisting of an encoder with a pre-modulation module and a GAN generator with F&W+ latent space.
Unbiased Multi-Modality Guidance for Image Inpainting
Image inpainting is an ill-posed problem to recover missing or damaged image content based on incomplete images with masks.
AutoTransition: Learning to Recommend Video Transition Effects
First we learn the embedding of video transitions through a video transition classification task.
Dual-Stream Transformer for Generic Event Boundary Captioning
This paper describes our champion solution for the CVPR2022 Generic Event Boundary Captioning (GEBC) competition.
Structured Context Transformer for Generic Event Boundary Detection
To capture temporal context information of each frame, we design the structure context transformer (SC-Transformer) by re-partitioning input frame sequence.
AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wild
Multi-animal tracking (MAT), a multi-object tracking (MOT) problem, is crucial for animal motion and behavior analysis and has many crucial applications such as biology, ecology and animal conservation.
Multi-Granularity Alignment Domain Adaptation for Object Detection
Domain adaptive object detection is challenging due to distinctive data distribution between source domain and target domain.
End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection
Generic event boundary detection aims to localize the generic, taxonomy-free event boundaries that segment videos into chunks.
Individual-Level Inverse Reinforcement Learning for Mean Field Games
This limitation invalidates existing IRL methods on MFGs with non-cooperative environments.
LD-ConGR: A Large RGB-D Video Dataset for Long-Distance Continuous Gesture Recognition
The dataset and experimental results presented in this paper are expected to boost the research of long-distance gesture recognition.
Towards Real-world X-ray Security Inspection: A High-Quality Benchmark and Lateral Inhibition Module for Prohibited Items Detection
In this work, we first present a High-quality X-ray (HiXray) security inspection image dataset, which contains 102, 928 common prohibited items of 8 categories.
Towards Real-World Prohibited Item Detection: A Large-Scale X-ray Benchmark
Towards real-world prohibited item detection, we collect a large-scale dataset, named as PIDray, which covers various cases in real-world scenarios for prohibited item detection, especially for deliberately hidden items.
Generic Event Boundary Detection Challenge at CVPR 2021 Technical Report: Cascaded Temporal Attention Network (CASTANET)
In this work, we design a Cascaded Temporal Attention Network (CASTANET) for GEBD, which is formed by three parts, the backbone network, the temporal attention module, and the classification module.
Ranked #1 on
Boundary Detection
on Kinetics-400
Adversarial Inverse Reinforcement Learning for Mean Field Games
However, existing IRL methods for MFGs are powerless to reason about uncertainties in demonstrated behaviours of individual agents.
Occluded Prohibited Items Detection: an X-ray Security Inspection Benchmark and De-occlusion Attention Module
Furthermore, to deal with the occlusion in X-ray images detection, we propose the De-occlusion Attention Module (DOAM), a plug-and-play module that can be easily inserted into and thus promote most popular detectors.
Spatial Attention Pyramid Network for Unsupervised Domain Adaptation
Specifically, we first build the spatial pyramid representation to capture context information of objects at different scales.
Rethinking Object Detection in Retail Stores
In this paper, we propose a new task, ie, simultaneously object localization and counting, abbreviated as Locount, which requires algorithms to localize groups of objects of interest with the number of instances.
Towards Interpretable and Robust Hand Detection via Pixel-wise Prediction
The lack of interpretability of existing CNN-based hand detection methods makes it difficult to understand the rationale behind their predictions.
Learning Semantic Neural Tree for Human Parsing
In this paper, we design a novel semantic neural tree for human parsing, which uses a tree architecture to encode physiological structure of human body, and designs a coarse to fine process in a cascade manner to generate accurate results.
SiamMan: Siamese Motion-aware Network for Visual Tracking
To reduce the impact of manually designed anchor boxes to adapt to different target motion patterns, we design the localization branch, which aims to coarsely localize the target to help the regression branch to generate accurate results.
Attention Convolutional Binary Neural Tree for Fine-Grained Visual Categorization
Specifically, we incorporate convolutional operations along edges of the tree structure, and use the routing functions in each node to determine the root-to-leaf computational paths within the tree.
Ranked #33 on
Fine-Grained Image Classification
on Stanford Cars
Fine-Grained Image Classification
Fine-Grained Visual Categorization
Guided Attention Network for Object Detection and Counting on Drones
Object detection and counting are related but challenging problems, especially for drone based scenes with small objects and cluttered background.
Computer Assisted Composition in Continuous Time
We address the problem of combining sequence models of symbolic music with user defined constraints.
Scale Invariant Fully Convolutional Network: Detecting Hands Efficiently
Existing hand detection methods usually follow the pipeline of multiple stages with high computation cost, i. e., feature extraction, region proposal, bounding box regression, and additional layers for rotated region detection.
Data Priming Network for Automatic Check-Out
In this paper, we propose a new data priming method to solve the domain adaptation problem.
