Search Results for author:
Found 39 papers, 19 papers with code
VITA: Video Instance Segmentation via Object Token Association
Specifically, we use an image object detector as a means of distilling object-specific contexts into object tokens.
Ranked #1 on
Video Instance Segmentation
on OVIS validation
Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints to Better Classify Objects in Videos
The set classifier is plug-and-playable to existing object trackers, and highly improves the performance of long-tailed object tracking.
UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection
Generic Event Boundary Detection (GEBD) is a newly suggested video understanding task that aims to find one level deeper semantic boundaries of events.
VISOLO: Grid-Based Space-Time Aggregation for Efficient Online Video Instance Segmentation
We also introduce cooperatively operating modules that aggregate information from available frames, in order to enrich the features for all subtasks in VIS.
UBoCo : Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection
Generic Event Boundary Detection (GEBD) is a newly suggested video understanding task that aims to find one level deeper semantic boundaries of events.
Winning the CVPR'2021 Kinetics-GEBD Challenge: Contrastive Learning Approach
Generic Event Boundary Detection (GEBD) is a newly introduced task that aims to detect "general" event boundaries that correspond to natural human perception.
Practical Single-Image Super-Resolution Using Look-Up Table
We train a deep SR network with a small receptive field and transfer the output values of the learned deep model to the LUT.
Tackling the Ill-Posedness of Super-Resolution Through Adaptive Target Generation
By the one-to-many nature of the super-resolution (SR) problem, a single low-resolution (LR) image can be mapped to many high-resolution (HR) images.
Video Instance Segmentation using Inter-Frame Communication Transformers
We propose a novel end-to-end solution for video instance segmentation (VIS) based on transformers.
Ranked #10 on
Video Instance Segmentation
on YouTube-VIS validation
Polygonal Point Set Tracking
Since the existing datasets are not suitable to validate our method, we build a new polygonal point set tracking dataset and demonstrate the superior performance of our method over the baselines and existing contour-based VOS methods.
Temporally smooth online action detection using cycle-consistent future anticipation
Many video understanding tasks work in the offline setting by assuming that the input video is given from the start to the end.
CAG-QIL: Context-Aware Actionness Grouping via Q Imitation Learning for Online Temporal Action Localization
Temporal action localization has been one of the most popular tasks in video understanding, due to the importance of detecting action instances in videos.
Large Scale Multi-Illuminant (LSMI) Dataset for Developing White Balance Algorithm Under Mixed Illumination
Images in our dataset are mostly captured with illuminants existing in the scene, and the ground truth illumination is computed by taking the difference between the images with different illumination combination.
Single-shot Path Integrated Panoptic Segmentation
Panoptic segmentation, which is a novel task of unifying instance segmentation and semantic segmentation, has attracted a lot of attention lately.
Cross-Identity Motion Transfer for Arbitrary Objects through Pose-Attentive Video Reassembling
To reduce the training-testing discrepancy of the self-supervised learning, a novel cross-identity training scheme is additionally introduced.
NTIRE 2020 Challenge on Perceptual Extreme Super-Resolution: Methods and Results
This paper reviews the NTIRE 2020 challenge on perceptual extreme super-resolution with focus on proposed solutions and results.
Deep Space-Time Video Upsampling Networks
Video super-resolution (VSR) and frame interpolation (FI) are traditional computer vision problems, and the performance have been improving by incorporating deep learning recently.
DMV: Visual Object Tracking via Part-level Dense Memory and Voting-based Retrieval
We propose a novel memory-based tracker via part-level dense memory and voting-based retrieval, called DMV.
Learning the Loss Functions in a Discriminative Space for Video Restoration
Our framework is similar to GANs in that we iteratively train two networks - a generator and a loss network.
Unsupervised Keypoint Learning for Guiding Class-Conditional Video Prediction
To generate future frames, we first detect keypoints of a moving object and predict future motion as a sequence of keypoints.
Copy-and-Paste Networks for Deep Video Inpainting
We propose a novel DNN-based framework called the Copy-and-Paste Networks for video inpainting that takes advantage of additional information in other frames of the video.
Ranked #4 on
Video Inpainting
on YouTube-VOS 2018 val
Onion-Peel Networks for Deep Video Completion
Given a set of reference images and a target image with holes, our network fills the hole by referring the contents in the reference images.
Fast User-Guided Video Object Segmentation by Interaction-and-Propagation Networks
We propose a new multi-round training scheme for the interactive video object segmentation so that the networks can learn how to understand the user's intention and update incorrect estimations during the training.
Ranked #6 on
Interactive Video Object Segmentation
on DAVIS 2017
(AUC-J metric)
Interactive Video Object Segmentation
Semantic Segmentation
+1
Video Object Segmentation using Space-Time Memory Networks
In our framework, the past frames with object masks form an external memory, and the current frame as the query is segmented using the mask information in the memory.
Ranked #4 on
Interactive Video Object Segmentation
on DAVIS 2017
(using extra training data)
Interactive Video Object Segmentation
One-shot visual object segmentation
+2
End-to-End Time-Lapse Video Synthesis from a Single Outdoor Image
Time-lapse videos usually contain visually appealing content but are often difficult and costly to create.
Text-Adaptive Generative Adversarial Networks: Manipulating Images with Natural Language
Our task aims to semantically modify visual attributes of an object in an image according to the text describing the new visual appearance.
Teaching Machines to Understand Baseball Games: Large-Scale Baseball Video Database for Multiple Video Understanding Tasks
A major obstacle in teaching machines to understand videos is the lack of training data, as creating temporal annotations for long videos requires a huge amount of human effort.
Deep Video Super-Resolution Network Using Dynamic Upsampling Filters Without Explicit Motion Compensation
We propose a novel end-to-end deep neural network that generates dynamic upsampling filters and a residual image, which are computed depending on the local spatio-temporal neighborhood of each pixel to avoid explicit motion compensation.
Ranked #3 on
Video Super-Resolution
on Vid4 - 4x upscaling
Fast Video Object Segmentation by Reference-Guided Mask Propagation
We validate our method on four benchmark sets that cover single and multiple object segmentation.
EPINET: A Fully-Convolutional Neural Network Using Epipolar Geometry for Depth from Light Field Images
Light field cameras capture both the spatial and the angular properties of light rays in space.
Modelling the Scene Dependent Imaging in Cameras with a Deep Neural Network
Often called as the radiometric calibration, the process of recovering RAW images from processed images (JPEG format in the sRGB color space) is essential for many computer vision tasks that rely on physically accurate radiance values.
Deep Semantics-Aware Photo Adjustment
Also, spatially varying photo adjustment methods have been studied by exploiting high-level features and semantic label maps.
Building Emotional Machines: Recognizing Image Emotions through Deep Neural Networks
In this paper, we focus on two high level features, the object and the background, and assume that the semantic information of images is a good cue for predicting emotion.
Approaching the Computational Color Constancy as a Classification Problem through Deep Learning
Computational color constancy refers to the problem of computing the illuminant color so that the images of a scene under varying illumination can be normalized to an image under the canonical illumination.
A Holistic Approach to Cross-Channel Image Noise Modeling and Its Application to Image Denoising
Modelling and analyzing noise in images is a fundamental task in many computer vision systems.
Do It Yourself Hyperspectral Imaging With Everyday Digital Cameras
In particular, due to the differences in spectral sensitivities of the cameras, different cameras yield different RGB measurements for the same spectral signal.
Complementary Sets of Shutter Sequences for Motion Deblurring
In this paper, we present a novel multi-image motion deblurring method utilizing the coded exposure technique.
Illuminant Aware Gamut-Based Color Transfer
Our method is unique in its considera- tion of the scene illumination and the constraint that the mapped image must be within the color gamut of the target image.
Color Transfer Using Probabilistic Moving Least Squares
This paper introduces a new color transfer method which is a process of transferring color of an image to match the color of another image of the same scene.
