Search Results for author:
Found 133 papers, 63 papers with code
SkipBERT: Efficient Inference with Shallow Layer Skipping
In this paper, we propose SkipBERT to accelerate BERT inference by skipping the computation of shallow layers.
Invisible Gas Detection: An RGB-Thermal Cross Attention Network and A New Benchmark
The widespread use of various chemical gases in industrial processes necessitates effective measures to prevent their leakage during transportation and storage, given their high toxicity.
FoldToken: Learning Protein Language via Vector Quantization and Beyond
Is there a foreign language describing protein sequences and structures simultaneously?
MapChange: Enhancing Semantic Change Detection with Temporal-Invariant Historical Maps Based on Deep Triplet Network
Semantic Change Detection (SCD) is recognized as both a crucial and challenging task in the field of image analysis.
Infinite forecast combinations based on Dirichlet process
Forecast combination integrates information from various sources by consolidating multiple forecast results from the target time series.
Deja Vu: Contextual Sparsity for Efficient LLMs at Inference Time
We show that contextual sparsity exists, that it can be accurately predicted, and that we can exploit it to speed up LLM inference in wall-clock time without compromising LLM's quality or in-context learning ability.
E4S: Fine-grained Face Swapping via Editing With Regional GAN Inversion
Based on this disentanglement, face swapping can be simplified as style and mask swapping.
Minimalist and High-Performance Semantic Segmentation with Plain Vision Transformers
Building upon the original motivations of plain ViTs, which are simplicity and generality, we explore high-performance `minimalist' systems to this end.
Ranked #1 on
Semantic Segmentation
on PASCAL Context
Revisiting the Temporal Modeling in Spatio-Temporal Predictive Learning under A Unified View
In this paper, we re-examine the two dominant temporal modeling approaches within the realm of spatio-temporal predictive learning, offering a unified perspective.
Draft & Verify: Lossless Large Language Model Acceleration via Self-Speculative Decoding
This approach is characterized by a two-stage process: drafting and verification.
Motion-Guided Masking for Spatiotemporal Representation Learning
This suggests that the random masking strategy that is inherited from the image MAE is less effective for video MAE.
Compress, Then Prompt: Improving Accuracy-Efficiency Trade-off of LLM Inference with Transferable Prompt
Thus, optimizing this accuracy-efficiency trade-off is crucial for the LLM deployment on commodity hardware.
Patch-based 3D Natural Scene Generation from a Single Example
We target a 3D generative model for general natural scenes that are typically unique and intricate.
Learning Anchor Transformations for 3D Garment Animation
Once the anchor transformations are found, per-vertex nonlinear displacements of the garment template can be regressed in a canonical space, which reduces the complexity of deformation space learning.
Improving Fast Adversarial Training with Prior-Guided Knowledge
This initialization is generated by using high-quality adversarial perturbations from the historical training process.
Selective Structured State-Spaces for Long-Form Video Understanding
To address this limitation, we present a novel Selective S4 (i. e., S5) model that employs a lightweight mask generator to adaptively select informative image tokens resulting in more efficient and accurate modeling of long-term spatiotemporal dependencies in videos.
Ranked #2 on
Video Classification
on Breakfast
CoordFill: Efficient High-Resolution Image Inpainting via Parameterized Coordinate Querying
Thanks to the proposed structure, we only encode the high-resolution image in a relatively low resolution for larger reception field capturing.
Skinned Motion Retargeting with Residual Perception of Motion Semantics & Geometry
Driven by our explored distance-based losses that explicitly model the motion semantics and geometry, these two modules can learn residual motion modifications on the source motion to generate plausible retargeted motion in a single inference without post-processing.
ACR: Attention Collaboration-based Regressor for Arbitrary Two-Hand Reconstruction
Our method significantly outperforms the best interacting-hand approaches on the InterHand2. 6M dataset while yielding comparable performance with the state-of-the-art single-hand methods on the FreiHand dataset.
Ranked #2 on
3D Interacting Hand Pose Estimation
on InterHand2.6M
CodeTalker: Speech-Driven 3D Facial Animation with Discrete Motion Prior
In this paper, we propose to cast speech-driven facial animation as a code query task in a finite proxy space of the learned codebook, which effectively promotes the vividness of the generated motions by reducing the cross-modal mapping uncertainty.
Ranked #4 on
3D Face Animation
on BEAT2
High-Quality Real-Time Rendering Using Subpixel Sampling Reconstruction
Generating high-quality, realistic rendering images for real-time applications generally requires tracing a few samples-per-pixel (spp) and using deep learning-based approaches to denoise the resulting low-spp images.
Truncate-Split-Contrast: A Framework for Learning from Mislabeled Videos
Thanks to Noise Contrastive Learning, the average classification accuracy improvement on Mini-Kinetics and Sth-Sth-V1 is over 1. 6\%.
Disentangled Image Colorization via Global Anchors
Our key insight is that several carefully located anchors could approximately represent the color distribution of an image, and conditioned on the anchor colors, we can predict the image color in a deterministic manner by utilizing internal correlation.
VideoReTalking: Audio-based Lip Synchronization for Talking Head Video Editing In the Wild
Our system disentangles this objective into three sequential tasks: (1) face video generation with a canonical expression; (2) audio-driven lip-sync; and (3) face enhancement for improving photo-realism.
Fine-Grained Face Swapping via Regional GAN Inversion
We rethink face swapping from the perspective of fine-grained face editing, \textit{i. e., ``editing for swapping'' (E4S)}, and propose a framework that is based on the explicit disentanglement of the shape and texture of facial components.
Holistic Evaluation of Language Models
We present Holistic Evaluation of Language Models (HELM) to improve the transparency of language models.
One Model to Edit Them All: Free-Form Text-Driven Image Manipulation with Semantic Modulations
Based on the visual latent space of StyleGAN[21] and text embedding space of CLIP[34], studies focus on how to map these two latent spaces for text-driven attribute manipulations.
Boosting the Transferability of Adversarial Attacks with Reverse Adversarial Perturbation
Furthermore, RAP can be naturally combined with many existing black-box attack techniques, to further boost the transferability.
Stability Analysis and Generalization Bounds of Adversarial Training
In adversarial machine learning, deep neural networks can fit the adversarial examples on the training dataset but have poor generalization ability on the test set.
Adaptive Smoothness-weighted Adversarial Training for Multiple Perturbations with Its Stability Analysis
Therefore, adversarial training for multiple perturbations (ATMP) is proposed to generalize the adversarial robustness over different perturbation types (in $\ell_1$, $\ell_2$, and $\ell_\infty$ norm-bounded perturbations).
Understanding Adversarial Robustness Against On-manifold Adversarial Examples
On synthetic datasets, theoretically, We prove that on-manifold adversarial examples are powerful, yet adversarial training focuses on off-manifold directions and ignores the on-manifold adversarial examples.
Control-Oriented Power Allocation for Integrated Satellite-UAV Networks
This letter presents a sensing-communication-computing-control (SC3) integrated satellite unmanned aerial vehicle (UAV) network, where the UAV is equipped with on-board sensors, mobile edge computing (MEC) servers, base stations and satellite communication module.
Towards Real-World Video Deblurring by Exploring Blur Formation Process
We believe the novel realistic synthesis pipeline and the corresponding RAW video dataset can help the community to easily construct customized blur datasets to improve real-world video deblurring performance largely, instead of laboriously collecting real data pairs.
HyP$^2$ Loss: Beyond Hypersphere Metric Space for Multi-label Image Retrieval
Image retrieval has become an increasingly appealing technique with broad multimedia application prospects, where deep hashing serves as the dominant branch towards low storage and efficient retrieval.
LocVTP: Video-Text Pre-training for Temporal Localization
To further enhance the temporal reasoning ability of the learned feature, we propose a context projection head and a temporal aware contrastive loss to perceive the contextual relationships.
Prior-Guided Adversarial Initialization for Fast Adversarial Training
Based on the observation, we propose a prior-guided FGSM initialization method to avoid overfitting after investigating several initialization strategies, improving the quality of the AEs during the whole training process.
Adversarial Attack
Adversarial Attack on Video Classification
Neural Parameterization for Dynamic Human Head Editing
Implicit radiance functions emerged as a powerful scene representation for reconstructing and rendering photo-realistic views of a 3D scene.
Fast Adversarial Training with Adaptive Step Size
While adversarial training and its variants have shown to be the most effective algorithms to defend against adversarial attacks, their extremely slow training process makes it hard to scale to large datasets like ImageNet.
Fine-tuning Language Models over Slow Networks using Activation Compression with Guarantees
Communication compression is a crucial technique for modern distributed learning systems to alleviate their communication bottlenecks over slower networks.
IDE-3D: Interactive Disentangled Editing for High-Resolution 3D-aware Portrait Synthesis
Existing 3D-aware facial generation methods face a dilemma in quality versus editability: they either generate editable results in low resolution or high-quality ones with no editing flexibility.
AdaptFormer: Adapting Vision Transformers for Scalable Visual Recognition
To address this challenge, we propose an effective adaptation approach for Transformer, namely AdaptFormer, which can adapt the pre-trained ViTs into many different image and video tasks efficiently.
Improving the Latent Space of Image Style Transfer
The content contrastive loss enables the encoder to retain more available details.
VDTR: Video Deblurring with Transformer
For multi-frame temporal modeling, we adapt Transformer to fuse multiple spatial features efficiently.
Deformable Video Transformer
Video transformers have recently emerged as an effective alternative to convolutional networks for action classification.
Multi-Robot Active Mapping via Neural Bipartite Graph Matching
Previous approaches either choose the frontier as the goal position via a myopic solution that hinders the time efficiency, or maximize the long-term value via reinforcement learning to directly regress the goal position, but does not guarantee the complete map construction.
UV Volumes for Real-time Rendering of Editable Free-view Human Performance
Neural volume rendering enables photo-realistic renderings of a human performer in free-view, a critical task in immersive VR/AR applications.
Unsupervised Pre-training for Temporal Action Localization Tasks
These pre-trained models can be sub-optimal for temporal localization tasks due to the inherent discrepancy between video-level classification and clip-level localization.
Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection
Following this principle, we propose to enrich the "diversity" of forgeries by synthesizing augmented forgeries with a pool of forgery configurations and strengthen the "sensitivity" to the forgeries by enforcing the model to predict the forgery configurations.
VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training
Pre-training video transformers on extra large-scale datasets is generally required to achieve premier performance on relatively small datasets.
Ranked #5 on
Self-Supervised Action Recognition
on HMDB51
LAS-AT: Adversarial Training with Learnable Attack Strategy
In this paper, we propose a novel framework for adversarial training by introducing the concept of "learnable attack strategy", dubbed LAS-AT, which learns to automatically produce attack strategies to improve the model robustness.
StyleHEAT: One-Shot High-Resolution Editable Talking Face Generation via Pre-trained StyleGAN
Our framework elevates the resolution of the synthesized talking face to 1024*1024 for the first time, even though the training dataset has a lower resolution.
Not All Patches are What You Need: Expediting Vision Transformers via Token Reorganizations
Second, by maintaining the same computational cost, our method empowers ViTs to take more image tokens as input for recognition accuracy improvement, where the image tokens are from higher resolution images.
Ranked #4 on
Efficient ViTs
on ImageNet-1K (with DeiT-S)
Reinforcement Learning-Empowered Mobile Edge Computing for 6G Edge Intelligence
Mobile edge computing (MEC) is considered a novel paradigm for computation-intensive and delay-sensitive tasks in fifth generation (5G) networks and beyond.
Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization
Inspired by recent success in unsupervised contrastive representation learning, we propose a novel denoised cross-video contrastive algorithm, aiming to enhance the feature discrimination ability of video snippets for accurate temporal action localization in the weakly-supervised setting.
PONet: Robust 3D Human Pose Estimation via Learning Orientations Only
Conventional 3D human pose estimation relies on first detecting 2D body keypoints and then solving the 2D to 3D correspondence problem. Despite the promising results, this learning paradigm is highly dependent on the quality of the 2D keypoint detector, which is inevitably fragile to occlusions and out-of-image absences. In this paper, we propose a novel Pose Orientation Net (PONet) that is able to robustly estimate 3D pose by learning orientations only, hence bypassing the error-prone keypoint detector in the absence of image evidence.
Ranked #80 on
3D Human Pose Estimation
on MPI-INF-3DHP
DistilCSE: Effective Knowledge Distillation For Contrastive Sentence Embeddings
To tackle that, we propose an effective knowledge distillation framework for contrastive sentence embeddings, termed DistilCSE.
Revitalizing CNN Attention via Transformers in Self-Supervised Visual Representation Learning
Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL.
Hallucinated Neural Radiance Fields in the Wild
This paper studies the problem of hallucinated NeRF: i. e., recovering a realistic NeRF at a different time of day from a group of tourism images.
FENeRF: Face Editing in Neural Radiance Fields
2D GANs can generate high fidelity portraits but with low view consistency.
Deblur-NeRF: Neural Radiance Fields from Blurry Images
We demonstrate that our method can be used on both camera motion blur and defocus blur: the two most common types of blur in real scenes.
TransAug: Translate as Augmentation for Sentence Embeddings
In this paper, we present TransAug (Translate as Augmentation), which provide the first exploration of utilizing translated sentence pairs as data augmentation for text, and introduce a two-stage paradigm to advances the state-of-the-art sentence embeddings.
Revitalizing CNN Attentions via Transformers in Self-Supervised Visual Representation Learning
Motivated by the transformers that explore visual attention effectively in recognition scenarios, we propose a CNN Attention REvitalization (CARE) framework to train attentive CNN encoders guided by transformers in SSL.
Boosting Fast Adversarial Training with Learnable Adversarial Initialization
Adversarial training (AT) has been demonstrated to be effective in improving model robustness by leveraging adversarial examples for training.
Motion-aware Contrastive Video Representation Learning via Foreground-background Merging
To alleviate such bias, we propose \textbf{F}oreground-b\textbf{a}ckground \textbf{Me}rging (FAME) to deliberately compose the moving foreground region of the selected video onto the static background of others.
EViT: Expediting Vision Transformers via Token Reorganizations
Second, by maintaining the same computational cost, our method empowers ViTs to take more image tokens as input for recognition accuracy improvement, where the image tokens are from higher resolution images.
Robust Physical-World Attacks on Face Recognition
Face recognition has been greatly facilitated by the development of deep neural networks (DNNs) and has been widely applied to many safety-critical applications.
High-Fidelity GAN Inversion for Image Attribute Editing
With a low bit-rate latent code, previous works have difficulties in preserving high-fidelity details in reconstructed and edited images.
Spatial-Separated Curve Rendering Network for Efficient and High-Resolution Image Harmonization
To this end, we propose a novel spatial-separated curve rendering network(S$^2$CRNet) for efficient and high-resolution image harmonization for the first time.
Ranked #12 on
Image Harmonization
on iHarmony4
EfficientCLIP: Efficient Cross-Modal Pre-training by Ensemble Confident Learning and Language Modeling
Extra rich non-paired single-modal text data is used for boosting the generalization of text branch.
Joint Multi-User Communication and Sensing Exploiting Both Signal and Environment Sparsity
As a potential technology feature for 6G wireless networks, the idea of sensing-communication integration requires the system not only to complete reliable multi-user communication but also to achieve accurate environment sensing.
End-to-End Adaptive Monte Carlo Denoising and Super-Resolution
We show in this work that Monte Carlo path tracing can be further accelerated by joint super-resolution and denoising (SRD) in post-processing.
Generalized One-Class Learning Using Pairs of Complementary Classifiers
One-class learning is the classic problem of fitting a model to the data for which annotations are available only for a single class.
Long-Short Temporal Contrastive Learning of Video Transformers
Our approach, named Long-Short Temporal Contrastive Learning (LSTCL), enables video transformers to learn an effective clip-level representation by predicting temporal context captured from a longer temporal extent.
Effective Slot Filling via Weakly-Supervised Dual-Model Learning
By using some particular weakly-labeled data, namely the plain phrases included in sentences, we propose a weaklysupervised slot filling approach.
Learning Log-Determinant Divergences for Positive Definite Matrices
There exist several similarity measures for comparing SPD matrices with documented benefits.
UPHDR-GAN: Generative Adversarial Network for High Dynamic Range Imaging with Unpaired Data
The ground truth images play a leading role in generating reasonable HDR images.
VX2TEXT: End-to-End Learning of Video-Based Text Generation From Multimodal Inputs
We present \textsc{Vx2Text}, a framework for text generation from multimodal inputs consisting of video plus text, speech, or audio.
DeepOIS: Gyroscope-Guided Deep Optical Image Stabilizer Compensation
In this work, we propose a deep network that compensates the motions caused by the OIS, such that the gyroscopes can be used for image alignment on the OIS cameras.
Towards Accurate Active Camera Localization
These approaches localize the camera in the discrete pose space and are agnostic to the localization-driven scene property, which restricts the camera pose accuracy in the coarse scale.
UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
By integrating these two components together, our method achieves the best performance for unsupervised optical flow learning on multiple leading benchmarks, including MPI-SIntel, KITTI 2012 and KITTI 2015.
Ranked #1 on
Optical Flow Estimation
on Sintel Final unsupervised
Practical Deep Raw Image Denoising on Mobile Devices
Deep learning-based image denoising approaches have been extensively studied in recent years, prevailing in many public benchmark datasets.
High-Fidelity 3D Digital Human Head Creation from RGB-D Selfies
We present a fully automatic system that can produce high-fidelity, photo-realistic 3D digital human heads with a consumer RGB-D selfie camera.
Two are Better than One: Joint Entity and Relation Extraction with Table-Sequence Encoders
In this work, we propose the novel {\em table-sequence encoders} where two different encoders -- a table encoder and a sequence encoder are designed to help each other in the representation learning process.
Ranked #2 on
Zero-shot Relation Triplet Extraction
on Wiki-ZSL
Joint Entity and Relation Extraction
named-entity-recognition
+5
Distributed ADMM with Synergetic Communication and Computation
In this paper, we propose a novel distributed alternating direction method of multipliers (ADMM) algorithm with synergetic communication and computation, called SCCD-ADMM, to reduce the total communication and computation cost of the system.
Fashion Captioning: Towards Generating Accurate Descriptions with Semantic Rewards
The goal of this work is to develop a novel learning framework for accurate and expressive fashion captioning.
Learning Color Compatibility in Fashion Outfits
Color compatibility is important for evaluating the compatibility of a fashion outfit, yet it was neglected in previous studies.
Pyramid: A Layered Model for Nested Named Entity Recognition
Its hidden state at layer l represents an l-gram in the input text, which is labeled only if its corresponding text region represents a complete entity mention.
Ranked #1 on
Nested Named Entity Recognition
on NNE
OccInpFlow: Occlusion-Inpainting Optical Flow Estimation by Unsupervised Learning
Occlusion is an inevitable and critical problem in unsupervised optical flow learning.
Enabling 5G on the Ocean: A Hybrid Satellite-UAV-Terrestrial Network Solution
In this paper, we study the integration of UAVs with existing MCNs, and investigate the potential gains of hybrid satellite-UAV-terrestrial networks for maritime coverage.
Spatio-Temporal Ranked-Attention Networks for Video Captioning
To this end, we propose a Spatio-Temporal and Temporo-Spatial (STaTS) attention model which, conditioned on the language state, hierarchically combines spatial and temporal attention to videos in two different orders: (i) a spatio-temporal (ST) sub-model, which first attends to regions that have temporal evolution, then temporally pools the features from these regions; and (ii) a temporo-spatial (TS) sub-model, which first decides a single frame to attend to, then applies spatial attention within that frame.
DeepMeshFlow: Content Adaptive Mesh Deformation for Robust Image Registration
Deep homography methods, on the other hand, are free from such problem by learning deep features for robust performance.
Not All Parts Are Created Equal: 3D Pose Estimation by Modeling Bi-Directional Dependencies of Body Parts
We model parts with higher DOFs like the elbows, as dependent components of the corresponding parts with lower DOFs like the torso, of which the 3D locations can be more reliably estimated.
Content-Aware Unsupervised Deep Homography Estimation
Homography estimation is a basic image alignment method in many applications.
Ranked #5 on
Homography Estimation
on S-COCO
Disentangled Image Matting
Most previous image matting methods require a roughly-specificed trimap as input, and estimate fractional alpha values for all pixels that are in the unknown region of the trimap.
Discriminative Video Representation Learning Using Support Vector Classifiers
With the features from the video as a positive bag and the irrelevant features as the negative bag, we cast an objective to learn a (nonlinear) hyperplane that separates the unknown useful features from the rest in a multiple instance learning formulation within a support vector machine setup.
GODS: Generalized One-class Discriminative Subspaces for Anomaly Detection
One-class learning is the classic problem of fitting a model to data for which annotations are available only for a single class.
Semi-supervised Skin Detection by Network with Mutual Guidance
In this paper we present a new data-driven method for robust skin detection from a single human portrait image.
Not All Parts Are Created Equal: 3D Pose Estimation by Modelling Bi-directional Dependencies of Body Parts
We model parts with higher DOFs like the elbows, as dependent components of the corresponding parts with lower DOFs like the torso, of which the 3D locations can be more reliably estimated.
Frame-Recurrent Video Inpainting by Robust Optical Flow Inference
Compared with image inpainting, performing this task on video presents new challenges such as how to preserving temporal consistency and spatial details, as well as how to handle arbitrary input video size and length fast and efficiently.
Learning Raw Image Denoising with Bayer Pattern Unification and Bayer Preserving Augmentation
In this paper, we present new data pre-processing and augmentation techniques for DNN-based raw image denoising.
Semi-Supervised Few-Shot Learning for Dual Question-Answer Extraction
In this paper, we redefine the problem as question-answer extraction, and present SAMIE: Self-Asking Model for Information Ixtraction, a semi-supervised model which dually learns to ask and to answer questions by itself.
When AWGN-based Denoiser Meets Real Noises
In this paper, we propose a novel approach to boost the performance of a real image denoiser which is trained only with synthetic pixel-independent noise data dominated by AWGN.
Ranked #2 on
Denoising
on Darmstadt Noise Dataset
GIF2Video: Color Dequantization and Temporal Interpolation of GIF images
In this paper, we propose GIF2Video, the first learning-based method for enhancing the visual quality of GIFs in the wild.
GeoNet: Deep Geodesic Networks for Point Cloud Analysis
Surface-based geodesic topology provides strong cues for object semantic analysis and geometric modeling.
Learning Discriminative Video Representations Using Adversarial Perturbations
As the perturbed features belong to data classes that are likely to be confused with the original features, the discriminative subspace will characterize parts of the feature space that are more representative of the original data, and thus may provide robust video representations.
Deep Portrait Image Completion and Extrapolation
We evaluate our method on public portrait image datasets, and show that it outperforms other state-of-art general image completion methods.
Graphics
Contrastive Video Representation Learning via Adversarial Perturbations
In this paper, we propose to use such perturbations within a novel contrastive learning setup to build negative samples, which are then used to produce improved video representations.
Ranked #42 on
Action Recognition
on HMDB-51
Video Inpainting by Jointly Learning Temporal Structure and Spatial Details
We present a new data-driven video inpainting method for recovering missing regions of video frames.
End-to-End Audio Visual Scene-Aware Dialog using Multimodal Attention-Based Video Features
We introduce a new dataset of dialogs about videos of human behaviors.
DocUNet: Document Image Unwarping via a Stacked U-Net
The network is trained on this dataset with various data augmentations to improve its generalization ability.
Ranked #4 on
SSIM
on DocUNet
(using extra training data)
Audio Visual Scene-Aware Dialog (AVSD) Challenge at DSTC7
Scene-aware dialog systems will be able to have conversations with users about the objects and events around them.
Video Representation Learning Using Discriminative Pooling
In an attempt to tackle this problem, we propose discriminative pooling, based on the notion that among the deep features generated on all short clips, there is at least one that characterizes the action.
Scale-recurrent Network for Deep Image Deblurring
In single image deblurring, the "coarse-to-fine" scheme, i. e. gradually restoring the sharp image on different resolutions in a pyramid, is very successful in both traditional optimization-based methods and recent neural-network-based approaches.
Ranked #3 on
Image Deblurring
on GoPro
(Params (M) metric, using extra
training data)
Human Action Forecasting by Learning Task Grammars
For effective human-robot interaction, it is important that a robotic assistant can forecast the next action a human will consider in a given task.
Deep Video Deblurring for Hand-Held Cameras
We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.
Zero-order Reverse Filtering
In this paper, we study an unconventional but practically meaningful reversibility problem of commonly used image filters.
Detail-revealing Deep Video Super-resolution
In this paper, we show that proper frame alignment and motion compensation is crucial for achieving high quality results.
Ranked #11 on
Video Super-Resolution
on Vid4 - 4x upscaling
Action Representation Using Classifier Decision Boundaries
Applying multiple instance learning in an SVM setup, we use the parameters of this separating hyperplane as a descriptor for the video.
Removing Shadows from Images of Documents
In this work, we automatically detect and remove distracting shadows from photographs of documents and other text-based items.
Ordered Pooling of Optical Flow Sequences for Action Recognition
Training of Convolutional Neural Networks (CNNs) on long video sequences is computationally expensive due to the substantial memory requirements and the massive number of parameters that deep architectures demand.
Deep Video Deblurring
We show that the features learned from this dataset extend to deblurring motion blur that arises due to camera shake in a wide range of videos, and compare the quality of results to a number of other baselines.
Coherent Parametric Contours for Interactive Video Object Segmentation
Interactive video segmentation systems aim at producing sub-pixel-level object boundaries for visual effect applications.
Automatic Fence Segmentation in Videos of Dynamic Scenes
We present a fully automatic approach to detect and segment fence-like occluders from a video clip.
Appearance Harmonization for Single Image Shadow Removal
In this work we propose a fully automatic shadow region harmonization approach that improves the appearance compatibility of the de-shadowed region as typically produced by previous methods.
Segmentation Rectification for Video Cutout via One-Class Structured Learning
Comprehensive experiments on both RGB and RGB-D data demonstrate that our simple and effective method significantly outperforms the segmentation propagation methods adopted in the state-of-the-art video cutout systems, and the results also suggest the potential usefulness of our method in image cutout system.
Blind Optical Aberration Correction by Exploring Geometric and Visual Priors
Furthermore, by investigating the visual artifacts of aberration degenerated images captured by consumer-level cameras, the non-uniform distribution of sharpness across color channels and the image lattice is exploited as visual priors, resulting in a novel strategy to utilize the guidance from the sharpest channel and local image regions to improve the overall performance and robustness.
Investigating Haze-relevant Features in A Learning Framework for Image Dehazing
Haze is one of the major factors that degrade outdoor images.
Deblurring Low-light Images with Light Streaks
Images taken in low-light conditions with handheld cameras are often blurry due to the required long exposure time.
Ranked #11 on
Deblurring
on RealBlur-R (trained on GoPro)
Supervised Semantic Gradient Extraction Using Linear-Time Optimization
This paper proposes a new supervised semantic edge and gradient extraction approach, which allows the user to roughly scribble over the desired region to extract semantically-dominant and coherent edges in it.
Handling Noise in Single Image Deblurring Using Directional Filters
Based on this observation, our method applies a series of directional filters at different orientations to the input image, and estimates an accurate Radon transform of the blur kernel from each filtered image.
Unsupervised Template Learning for Fine-Grained Object Recognition
It differs from recognition of basic categories, such as humans, tables, and computers, in that there are global similarities in shape or structure shared within a category, and the differences are in the details of the object parts.
Avoiding False Positive in Multi-Instance Learning
In multi-instance learning, there are two kinds of prediction failure, i. e., false negative and false positive.
