Search Results for author:
Found 68 papers, 30 papers with code
GenCLIP: Generalizing CLIP Prompts for Zero-shot Anomaly Detection
Zero-shot anomaly detection (ZSAD) aims to identify anomalies in unseen categories by leveraging CLIP's zero-shot capabilities to match text prompts with visual features.
CoMoGaussian: Continuous Motion-Aware Gaussian Splatting from Motion-Blurred Images
3D Gaussian Splatting (3DGS) has gained significant attention for their high-quality novel view rendering, motivating research to address real-world challenges.
Find First, Track Next: Decoupling Identification and Propagation in Referring Video Object Segmentation
This reference is then utilized by a dedicated propagation module to track and segment the object across the entire video.
Ranked #1 on
Referring Video Object Segmentation
on Ref-DAVIS17
CoCoGaussian: Leveraging Circle of Confusion for Gaussian Splatting from Defocused Images
While conventional methods depend on sharp images for accurate scene reconstruction, real-world scenarios are often affected by defocus blur due to finite depth of field, making it essential to account for realistic 3D scene representation.
Elevating Flow-Guided Video Inpainting with Reference Generation
Powered by a strong generative model, our method not only significantly enhances frame-level quality for object removal but also synthesizes new content in the missing areas based on user-provided text prompts.
Ranked #1 on
Video Inpainting
on HQVI (2K)
STATIC : Surface Temporal Affine for TIme Consistency in Video Monocular Depth Estimation
For static area, the Masked Static (MS) module enhances temporal consistency by focusing on stable regions.
Effective SAM Combination for Open-Vocabulary Semantic Segmentation
Open-vocabulary semantic segmentation aims to assign pixel-level labels to images across an unlimited range of classes.
Transforming Static Images Using Generative Models for Video Salient Object Detection
This ability allows the model to generate plausible optical flows, preserving semantic integrity while reflecting the independent motion of scene elements.
Ranked #1 on
Video Salient Object Detection
on DAVSOD-easy35
(using extra training data)
Multi-Scale Feature Prediction with Auxiliary-Info for Neural Image Compression
Finally, we introduce Auxiliary info-guided Parameter Estimation (APE) module, which predicts the approximation of the latent vector and estimates the probability distribution of these residuals.
Video Diffusion Models are Strong Video Inpainter
However, it has limitations such as the inaccuracy of optical flow prediction and the propagation of noise over time.
WWW: Where, Which and Whatever Enhancing Interpretability in Multimodal Deepfake Detection
All current benchmarks for multimodal deepfake detection manipulate entire frames using various generation techniques, resulting in oversaturated detection accuracies exceeding 94% at the video-level classification.
Enhancing Temporal Action Localization: Advanced S6 Modeling with Recurrent Mechanism
Temporal Action Localization (TAL) is a critical task in video analysis, identifying precise start and end times of actions.
Ranked #1 on
Temporal Action Localization
on HACS
Improving Unsupervised Video Object Segmentation via Fake Flow Generation
Unsupervised video object segmentation (VOS), also known as video salient object detection, aims to detect the most prominent object in a video at the pixel level.
Ranked #1 on
Unsupervised Video Object Segmentation
on FBMS test
ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion
Self-supervised multi-frame monocular depth estimation relies on the geometric consistency between successive frames under the assumption of a static scene.
Sparse-DeRF: Deblurred Neural Radiance Fields from Sparse View
Recent studies construct deblurred neural radiance fields~(DeRF) using dozens of blurry images, which are not practical scenarios if only a limited number of blurry images are available.
CRiM-GS: Continuous Rigid Motion-Aware Gaussian Splatting from Motion-Blurred Images
3D Gaussian Splatting (3DGS) has gained significant attention for their high-quality novel view rendering, motivating research to address real-world challenges.
Separate and Reconstruct: Asymmetric Encoder-Decoder for Speech Separation
To achieve this, an asymmetric strategy is presented in which the encoder and decoder are partitioned to perform distinct processing in separation tasks.
Ranked #1 on
Speech Separation
on WSJ0-2mix
SMURF: Continuous Dynamics for Motion-Deblurring Radiance Fields
Neural radiance fields (NeRF) has attracted considerable attention for their exceptional ability in synthesizing novel views with high fidelity.
FIMP: Future Interaction Modeling for Multi-Agent Motion Prediction
Multi-agent motion prediction is a crucial concern in autonomous driving, yet it remains a challenge owing to the ambiguous intentions of dynamic agents and their intricate interactions.
Synchronizing Vision and Language: Bidirectional Token-Masking AutoEncoder for Referring Image Segmentation
While these methods match language features with image features to effectively identify likely target objects, they often struggle to correctly understand contextual information in complex and ambiguous sentences and scenes.
Treating Motion as Option with Output Selection for Unsupervised Video Object Segmentation
Unsupervised video object segmentation (VOS) is a task that aims to detect the most salient object in a video without external guidance about the object.
Ranked #3 on
Unsupervised Video Object Segmentation
on FBMS test
Adaptive Graph Convolution Module for Salient Object Detection
Salient object detection (SOD) is a task that involves identifying and segmenting the most visually prominent object in an image.
Guided Slot Attention for Unsupervised Video Object Segmentation
Unsupervised video object segmentation aims to segment the most prominent object in a video sequence.
One-Shot Video Inpainting
Usually, a video sequence and object segmentation masks for all frames are required as the input for this task.
Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection
Image reconstruction-based anomaly detection has recently been in the spotlight because of the difficulty of constructing anomaly datasets.
Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning
Furthermore, as the relationship between context and motion is important in order to identify the anomalies in complex and diverse scenes, we propose a Context--Motion Interrelation Module (CoMo), which models the relationship between the appearance of the surroundings and motion, rather than utilizing only temporal dependencies or motion information.
Feature Disentanglement Learning with Switching and Aggregation for Video-based Person Re-Identification
In video person re-identification (Re-ID), the network must consistently extract features of the target person from successive frames.
Occluded Person Re-Identification via Relational Adaptive Feature Correction Learning
Occluded person re-identification (Re-ID) in images captured by multiple cameras is challenging because the target person is occluded by pedestrians or objects, especially in crowded scenes.
Leveraging Spatio-Temporal Dependency for Skeleton-Based Action Recognition
In this paper, we propose the Spatio-Temporal Curve Network (STC-Net) to effectively leverage the spatio-temporal dependency of the human skeleton.
Dual Prototype Attention for Unsupervised Video Object Segmentation
Unsupervised video object segmentation (VOS) aims to detect and segment the most salient object in videos.
Ranked #2 on
Unsupervised Video Object Segmentation
on FBMS test
DP-NeRF: Deblurred Neural Radiance Field with Physical Scene Priors
The few studies that have investigated NeRF for blurred images have not considered geometric and appearance consistency in 3D space, which is one of the most important factors in 3D reconstruction.
Boundary-aware Camouflaged Object Detection via Deformable Point Sampling
The proposed DPS-Net utilizes a Deformable Point Sampling transformer (DPS transformer) that can effectively capture sparse local boundary information of significant object boundaries in COD using a deformable point sampling method.
FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection
Feature embedding-based methods have shown exceptional performance in detecting industrial anomalies by comparing features of target images with normal images.
Ranked #46 on
Anomaly Detection
on MVTec AD
(using extra training data)
Unsupervised Video Object Segmentation via Prototype Memory Network
The proposed model effectively extracts the RGB and motion information by extracting superpixel-based component prototypes from the input RGB images and optical flow maps.
Ranked #9 on
Unsupervised Video Object Segmentation
on FBMS test
Pixel-Level Equalized Matching for Video Object Segmentation
Feature similarity matching, which transfers the information of the reference frame to the query frame, is a key component in semi-supervised video object segmentation.
Treating Motion as Option to Reduce Motion Dependency in Unsupervised Video Object Segmentation
Unsupervised video object segmentation (VOS) aims to detect the most salient object in a video sequence at the pixel level.
Ranked #6 on
Unsupervised Video Object Segmentation
on FBMS test
Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition
Graph convolutional networks (GCNs) are the most commonly used methods for skeleton-based action recognition and have achieved remarkable performance.
Expanded Adaptive Scaling Normalization for End to End Image Compression
Then, we increase the receptive field to make the adaptive rescaling module consider the spatial correlation.
NIR-to-VIS Face Recognition via Embedding Relations and Coordinates of the Pairwise Features
With the proposed module, we achieve 14. 81% rank-1 accuracy and 15. 47% verification rate of 0. 1% FAR improvements compare to two baseline models.
N-RPN: Hard Example Learning for Region Proposal Networks
The region proposal task is to generate a set of candidate regions that contain an object.
SPSN: Superpixel Prototype Sampling Network for RGB-D Salient Object Detection
However, despite advances in deep learning-based methods, RGB-D SOD is still challenging due to the large domain gap between an RGB image and the depth map and low-quality depth maps.
Ranked #4 on
RGB-D Salient Object Detection
on NJU2K
Tackling Background Distraction in Video Object Segmentation
Semi-supervised video object segmentation (VOS) aims to densely track certain designated objects in videos.
Exploring Temporally Dynamic Data Augmentation for Video Recognition
The magnitude of augmentation operations on each frame is changed by an effective mechanism, Fourier Sampling that parameterizes diverse, smooth, and realistic temporal variations.
Exploring Discontinuity for Video Frame Interpolation
Lastly, we propose loss functions to give supervisions of the discontinuous motion areas which can be applied along with FTM and D-map.
RandomSEMO: Normality Learning Of Moving Objects For Video Anomaly Detection
Moreover, MOLoss urges the model to focus on learning normal objects captured within RandomSEMO by amplifying the loss on the pixels near the moving objects.
Saliency Detection via Global Context Enhanced Feature Fusion and Edge Weighted Loss
1) Indiscriminately integrating the encoder feature, which contains spatial information for multiple objects, and the decoder feature, which contains global information of the salient object, is likely to convey unnecessary details of non-salient objects to the decoder, hindering saliency detection.
Ranked #1 on
RGB Salient Object Detection
on PASCAL-S
Pixel-Level Bijective Matching for Video Object Segmentation
Before finding the best matches for the query frame pixels, the optimal matches for the reference frame pixels are first considered to prevent each reference frame pixel from being overly referenced.
MKConv: Multidimensional Feature Representation for Point Cloud Analysis
In this paper, we present Multidimensional Kernel Convolution (MKConv), a novel convolution operator that learns to transform the point feature representation from a vector to a multidimensional matrix.
Ranked #16 on
3D Part Segmentation
on ShapeNet-Part
EdgeConv with Attention Module for Monocular Depth Estimation
Monocular depth estimation is an especially important task in robotics and autonomous driving, where 3D structural information is essential.
FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation
Video anomaly detection has gained significant attention due to the increasing requirements of automatic monitoring for surveillance videos.
Anomaly Detection In Surveillance Videos
Optical Flow Estimation
+1
Robust Lane Detection via Expanded Self Attention
Modern deep learning methods achieve high performance in lane detection, but it is still difficult to accurately detect lanes in challenging situations such as congested roads and extreme lighting conditions.
Ranked #49 on
Lane Detection
on CULane
Regularization Strategy for Point Cloud via Rigidly Mixed Sample
Data augmentation is an effective regularization strategy to alleviate the overfitting, which is an inherent drawback of the deep neural networks.
Ranked #4 on
3D Point Cloud Classification
on ModelNet40-C
Test-Time Adaptation for Out-of-distributed Image Inpainting
From this test-time adaptation, our network can exploit externally learned image priors from the pre-trained features as well as the internal prior of the test image explicitly.
A NIR-to-VIS face recognition via part adaptive and relation attention module
In the face recognition application scenario, we need to process facial images captured in various conditions, such as at night by near-infrared (NIR) surveillance cameras.
Multi-object tracking with self-supervised associating network
So in this paper, we propose a novel self-supervised learning method using a lot of short videos which has no human labeling, and improve the tracking performance through the re-identification network trained in the self-supervised manner to solve the lack of training data problem.
Unsupervised Video Anomaly Detection via Normalizing Flows with Implicit Latent Features
For the complex distribution of normal scenes, we suggest normal density estimation of ITAE features through normalizing flow (NF)-based generative models to learn the tractable likelihoods and identify anomalies using out of distribution detection.
Smoother Network Tuning and Interpolation for Continuous-level Image Processing
Extensive results for various image processing tasks indicate that the performance of FTN is comparable in multiple continuous levels, and is significantly smoother and lighter than that of other frameworks.
Enhanced Standard Compatible Image Compression Framework based on Auxiliary Codec Networks
The postprocessing network increases the quality of decoded images using an example-based learning.
PMVOS: Pixel-Level Matching-Based Video Object Segmentation
Semi-supervised video object segmentation (VOS) aims to segment arbitrary target objects in video when the ground truth segmentation mask of the initial frame is provided.
Learning Temporally Invariant and Localizable Features via Data Augmentation for Video Recognition
Based on our novel temporal data augmentation algorithms, video recognition performances are improved using only a limited amount of training data compared to the spatial-only data augmentation algorithms, including the 1st Visual Inductive Priors (VIPriors) for data-efficient action recognition challenge.
Extrapolative-Interpolative Cycle-Consistency Learning for Video Frame Extrapolation
Unlike previous studies that usually have been focused on the design of modules or construction of networks, we propose a novel Extrapolative-Interpolative Cycle (EIC) loss using pre-trained frame interpolation module to improve extrapolation performance.
False Positive Removal for 3D Vehicle Detection with Penetrated Point Classifier
Recently, researchers have been leveraging LiDAR point cloud for higher accuracy in 3D vehicle detection.
Regularized Adaptation for Stable and Efficient Continuous-Level Learning on Image Processing Networks
In this paper, we propose a novel continuous-level learning framework using a Filter Transition Network (FTN) which is a non-linear module that easily adapt to new levels, and is regularized to prevent undesirable side-effects.
Relational Deep Feature Learning for Heterogeneous Face Recognition
Due to the lack of databases, HFR methods usually exploit the pre-trained features on a large-scale visual database that contain general facial information.
CRVOS: Clue Refining Network for Video Object Segmentation
The encoder-decoder based methods for semi-supervised video object segmentation (Semi-VOS) have received extensive attention due to their superior performances.
Ranked #60 on
Semi-Supervised Video Object Segmentation
on DAVIS 2016
AD-VO: Scale-Resilient Visual Odometry Using Attentive Disparity Map
Visual odometry is an essential key for a localization module in SLAM systems.
AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation
Video frame interpolation is one of the most challenging tasks in video processing research.
Ranked #16 on
Video Frame Interpolation
on MSU Video Frame Interpolation
(LPIPS metric)
