Search Results for author:
Found 303 papers, 146 papers with code
Video Object Detection via Object-level Temporal Aggregation
While single-image object detectors can be naively applied to videos in a frame-by-frame fashion, the prediction is often temporally inconsistent.
Adversarial Training with Bi-directional Likelihood Regularization for Visual Classification
We call such a new robust training strategy the adversarial training with bi-directional likelihood regularization (ATBLR) method.
SAMPLING: Scene-adaptive Hierarchical Multiplane Images Representation for Novel View Synthesis from a Single Image
Recent novel view synthesis methods obtain promising results for relatively small scenes, e. g., indoor environments and scenes with a few objects, but tend to fail for unbounded outdoor scenes with a single image as input.
Text-driven Editing of 3D Scenes without Retraining
To tackle these issues, we introduce a text-driven editing method, termed DN2N, which allows for the direct acquisition of a NeRF model with universal editing capabilities, eliminating the requirement for retraining.
CiteTracker: Correlating Image and Text for Visual Tracking
Existing visual tracking methods typically take an image patch as the reference of the target to perform tracking.
Delving into Motion-Aware Matching for Monocular 3D Object Tracking
In this paper, we find that the motion cue of objects along different time frames is critical in 3D multi-object tracking, which is less explored in existing monocular-based approaches.
Dual Associated Encoder for Face Restoration
Restoring facial details from low-quality (LQ) images has remained a challenging problem due to its ill-posedness induced by various degradations in the wild.
Foundational Models Defining a New Era in Vision: A Survey and Outlook
Vision systems to see and reason about the compositional nature of visual scenes are fundamental to understanding our world.
CLR: Channel-wise Lightweight Reprogramming for Continual Learning
Reprogramming parameters are task-specific and exclusive to each task, which makes our method immune to catastrophic forgetting.
Self-regulating Prompts: Foundational Model Adaptation without Forgetting
To the best of our knowledge, this is the first regularization framework for prompt learning that avoids overfitting by jointly attending to pre-trained model features, the training trajectory during prompting, and the textual diversity.
Ranked #1 on
Prompt Engineering
on ImageNet V2
VideoGLUE: Video General Understanding Evaluation of Foundation Models
We evaluate existing foundation models video understanding capabilities using a carefully designed experiment protocol consisting of three hallmark tasks (action recognition, temporal localization, and spatiotemporal localization), eight datasets well received by the community, and four adaptation methods tailoring a foundation model (FM) for a downstream task.
SPAE: Semantic Pyramid AutoEncoder for Multimodal Generation with Frozen LLMs
In this work, we introduce Semantic Pyramid AutoEncoder (SPAE) for enabling frozen LLMs to perform both understanding and generation tasks involving non-linguistic modalities such as images or videos.
ARTIC3D: Learning Robust Articulated 3D Shapes from Noisy Web Image Collections
Second, we perform diffusion-guided 3D optimization to estimate shape and texture that are of high-fidelity and faithful to input images.
Counting Crowds in Bad Weather
Crowd counting has recently attracted significant attention in the field of computer vision due to its wide applications to image understanding.
AIMS: All-Inclusive Multi-Level Segmentation
Despite the progress of image segmentation for accurate visual entity segmentation, completing the diverse requirements of image editing applications for different-level region-of-interest selections remains unsolved.
A Tale of Two Features: Stable Diffusion Complements DINO for Zero-Shot Semantic Correspondence
Text-to-image diffusion models have made significant advances in generating and editing high-quality images.
Motion-Conditioned Diffusion Model for Controllable Video Synthesis
In response to this gap, we introduce MCDiff, a conditional diffusion model that generates a video from a starting image frame and a set of strokes, which allow users to specify the intended content and dynamics for synthesis.
Video Generation Beyond a Single Clip
We tackle the long video generation problem, i. e.~generating videos beyond the output length of video generation models.
Generative Multiplane Neural Radiance for 3D-Aware Image Generation
We present a method to efficiently generate 3D-aware high-resolution images that are view-consistent across multiple target views.
Burstormer: Burst Image Restoration and Enhancement Transformer
Unlike existing methods, the proposed alignment module not only aligns burst features but also exchanges feature information and maintains focused communication with the reference frame through the proposed reference-based feature enrichment mechanism, which facilitates handling complex motions.
Spatiotemporally Discriminative Video-Language Pre-Training with Text Grounding
Most of existing video-language pre-training methods focus on instance-level alignment between video clips and captions via global contrastive learning but neglect rich fine-grained local information, which is of importance to downstream tasks requiring temporal localization and semantic reasoning.
SwiftFormer: Efficient Additive Attention for Transformer-based Real-time Mobile Vision Applications
Using our proposed efficient additive attention, we build a series of models called "SwiftFormer" which achieves state-of-the-art performance in terms of both accuracy and mobile inference speed.
Unified Visual Relationship Detection with Vision and Language Models
To address this challenge, we propose UniVRD, a novel bottom-up method for Unified Visual Relationship Detection by leveraging vision and language models (VLMs).
Human-Object Interaction Detection
Relationship Detection
+2
InfiniCity: Infinite-Scale City Synthesis
Toward infinite-scale 3D city synthesis, we propose a novel framework, InfiniCity, which constructs and renders an unconstrainedly large and 3D-grounded environment from random noises.
PanopticPartFormer++: A Unified and Decoupled View for Panoptic Part Segmentation
Third, inspired by Mask2Former, based on our meta-architecture, we propose Panoptic-PartFormer++ and design a new part-whole cross-attention scheme to boost part segmentation qualities further.
Muse: Text-To-Image Generation via Masked Generative Transformers
Compared to pixel-space diffusion models, such as Imagen and DALL-E 2, Muse is significantly more efficient due to the use of discrete tokens and requiring fewer sampling iterations; compared to autoregressive models, such as Parti, Muse is more efficient due to the use of parallel decoding.
Ranked #20 on
Text-to-Image Generation
on COCO
Self-Supervised Super-Plane for Neural 3D Reconstruction
In this work, we introduce a self-supervised super-plane constraint by exploring the free geometry cues from the predicted surface, which can further regularize the reconstruction of plane regions without any other ground truth annotations.
Beyond SOT: Tracking Multiple Generic Objects at Once
Our approach achieves a 4x faster run-time in case of 10 concurrent objects compared to tracking each object independently and outperforms existing single object trackers on our new benchmark.
Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble
Automatically estimating 3D skeleton, shape, camera viewpoints, and part articulation from sparse in-the-wild image ensembles is a severely under-constrained and challenging problem.
Learning Object-level Point Augmentor for Semi-supervised 3D Object Detection
In this work, we propose an object-level point augmentor (OPA) that performs local transformations for semi-supervised 3D object detection.
MAGVIT: Masked Generative Video Transformer
We introduce the MAsked Generative VIdeo Transformer, MAGVIT, to tackle various video synthesis tasks with a single model.
Ranked #1 on
Video Generation
on UCF-101
DIP: Differentiable Interreflection-aware Physics-based Inverse Rendering
To model the illumination of a scene, existing inverse rendering works either completely ignore the indirect illumination or model it by coarse approximations, leading to sub-optimal illumination, geometry, and material prediction of the scene.
Learning to Dub Movies via Hierarchical Prosody Models
Given a piece of text, a video clip and a reference audio, the movie dubbing (also known as visual voice clone V2C) task aims to generate speeches that match the speaker's emotion presented in the video using the desired speaker voice as reference.
Consistency-Aware Anchor Pyramid Network for Crowd Localization
Crowd localization aims to predict the spatial position of humans in a crowd scenario.
UNETR++: Delving into Efficient and Accurate 3D Medical Image Segmentation
Owing to the success of transformer models, recent works study their applicability in 3D medical segmentation tasks.
Progressive Multi-resolution Loss for Crowd Counting
Crowd counting is usually handled in a density map regression fashion, which is supervised via a L2 loss between the predicted density map and ground truth.
Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection
Weakly supervised video anomaly detection aims to identify abnormal events in videos using only video-level labels.
Self-supervised AutoFlow
Recently, AutoFlow has shown promising results on learning a training set for optical flow, but requires ground truth labels in the target domain to compute its search metric.
Improving Zero-shot Generalization and Robustness of Multi-modal Models
We also show that our method improves across ImageNet shifted datasets, four other datasets, and other model architectures such as LiT.
Exploiting Category Names for Few-Shot Classification with Vision-Language Models
Vision-language foundation models pretrained on large-scale data provide a powerful tool for many visual understanding tasks.
Diffusion-Based Scene Graph to Image Generation with Masked Contrastive Pre-Training
Generating images from graph-structured inputs, such as scene graphs, is uniquely challenging due to the difficulty of aligning nodes and connections in graphs with objects and their relations in images.
High-Quality Entity Segmentation
It improves mask prediction by fusing high-res image crops that provide more fine-grained image details and the full image.
ScoreMix: A Scalable Augmentation Strategy for Training GANs with Limited Data
Then, we optimize the augmented samples by minimizing the norms of the data scores, i. e., the gradients of the log-density functions.
GAN-based Facial Attribute Manipulation
Facial Attribute Manipulation (FAM) aims to aesthetically modify a given face image to render desired attributes, which has received significant attention due to its broad practical applications ranging from digital entertainment to biometric forensics.
Diffusion Models: A Comprehensive Survey of Methods and Applications
This survey aims to provide a contextualized, in-depth look at the state of diffusion models, identifying the key areas of focus and pointing to potential areas for further exploration.
Learning Visibility for Robust Dense Human Body Estimation
An alternative approach is to estimate dense vertices of a predefined template body in the image space.
3D Vision with Transformers: A Survey
The success of the transformer architecture in natural language processing has recently triggered attention in the computer vision field.
Automatically Discovering Novel Visual Categories with Self-supervised Prototype Learning
In the first stage, we obtain a robust feature extractor, which could serve for all images with base and novel categories.
Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models
Utilizing vision and language models (VLMs) pre-trained on large-scale image-text pairs is becoming a promising paradigm for open-vocabulary visual recognition.
Ranked #1 on
Zero-Shot Action Recognition
on HMDB51
LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery
In this work, we propose a practical problem setting to estimate 3D pose and shape of animals given only a few (10-30) in-the-wild images of a particular animal species (say, horse).
FlowNAS: Neural Architecture Search for Optical Flow Estimation
To address this issue, we propose a neural architecture search method named FlowNAS to automatically find the better encoder architecture for flow estimation task.
Unveiling The Mask of Position-Information Pattern Through the Mist of Image Features
Recent studies show that paddings in convolutional neural networks encode absolute position information which can negatively affect the model performance for certain tasks.
Learning Enriched Features for Fast Image Restoration and Enhancement
In the former case, spatial details are preserved but the contextual information cannot be precisely encoded.
An Extendable, Efficient and Effective Transformer-based Object Detector
Transformers have been widely used in numerous vision problems especially for visual recognition and detection.
Autoregressive 3D Shape Generation via Canonical Mapping
With the capacity of modeling long-range dependencies in sequential data, transformers have shown remarkable performances in a variety of generative tasks such as image, audio, and text generation.
Neural Rendering of Humans in Novel View and Pose from Monocular Video
We accomplish this by utilizing both the human pose that models the body shape as well as point clouds that partially cover the human as input.
Adaptive Transformers for Robust Few-shot Cross-domain Face Anti-spoofing
While recent face anti-spoofing methods perform well under the intra-domain setups, an effective approach needs to account for much larger appearance variations of images acquired in complex scenes with different sensors for robust performance.
V2X-ViT: Vehicle-to-Everything Cooperative Perception with Vision Transformer
In this paper, we investigate the application of Vehicle-to-Everything (V2X) communication to improve the perception performance of autonomous vehicles.
Ranked #1 on
3D Object Detection
on V2XSet
Deep Image Deblurring: A Survey
Image deblurring is a classic problem in low-level computer vision with the aim to recover a sharp image from a blurred input image.
InOut: Diverse Image Outpainting via GAN Inversion
Existing image outpainting methods pose the problem as a conditional image-to-image translation task, often generating repetitive structures and textures by replicating the content available in the input image.
Towards a Unified Foundation Model: Jointly Pre-Training Transformers on Unpaired Images and Text
The experiments show that the resultant unified foundation transformer works surprisingly well on both the vision-only and text-only tasks, and the proposed knowledge distillation and gradient masking strategy can effectively lift the performance to approach the level of separately-trained models.
An Informative Tracking Benchmark
Along with the rapid progress of visual tracking, existing benchmarks become less informative due to redundancy of samples and weak discrimination between current trackers, making evaluations on all datasets extremely time-consuming.
Contextualized Spatio-Temporal Contrastive Learning with Self-Supervision
Modern self-supervised learning algorithms typically enforce persistency of instance representations across views.
CA-SSL: Class-Agnostic Semi-Supervised Learning for Detection and Segmentation
To improve instance-level detection/segmentation performance, existing self-supervised and semi-supervised methods extract either task-unrelated or task-specific training signals from unlabeled data.
Exploring Temporal Granularity in Self-Supervised Video Representation Learning
The training objective consists of two parts: a fine-grained temporal learning objective to maximize the similarity between corresponding temporal embeddings in the short clip and the long clip, and a persistent temporal learning objective to pull together global embeddings of the two clips.
MC-Blur: A Comprehensive Benchmark for Image Deblurring
Blur artifacts can seriously degrade the visual quality of images, and numerous deblurring methods have been proposed for specific scenarios.
Exploring Cross-Video and Cross-Modality Signals for Weakly-Supervised Audio-Visual Video Parsing
The audio-visual video parsing task aims to temporally parse a video into audio or visual event categories.
Learning Discriminative Shrinkage Deep Networks for Image Deconvolution
Most existing methods usually formulate the non-blind deconvolution problem into a maximum-a-posteriori framework and address it by manually designing kinds of regularization terms and data terms of the latent clear images.
Learning Continuous Environment Fields via Implicit Functions
We propose a novel scene representation that encodes reaching distance -- the distance between any position in the scene to a goal along a feasible trajectory.
Video Frame Interpolation Transformer
Existing methods for video interpolation heavily rely on deep convolution neural networks, and thus suffer from their intrinsic limitations, such as content-agnostic kernel weights and restricted receptive field.
Hierarchical Modular Network for Video Captioning
(II) Predicate level, which learns the actions conditioned on highlighted objects and is supervised by the predicate in captions.
Class-agnostic Object Detection with Multi-modal Transformer
This has been a long-standing question in computer vision.
Ranked #1 on
Class-agnostic Object Detection
on COCO
Restormer: Efficient Transformer for High-Resolution Image Restoration
Since convolutional neural networks (CNNs) perform well at learning generalizable image priors from large-scale data, these models have been extensively applied to image restoration and related tasks.
Ranked #1 on
Grayscale Image Denoising
on Urban100 sigma15
Correcting Face Distortion in Wide-Angle Videos
Video blogs and selfies are popular social media formats, which are often captured by wide-angle cameras to show human subjects and expanded background.
Video Salient Object Detection via Contrastive Features and Attention Modules
Video salient object detection aims to find the most visually distinctive objects in a video.
Semi-supervised Multi-task Learning for Semantics and Depth
Multi-Task Learning (MTL) aims to enhance the model generalization by sharing representations between related tasks for better performance.
ViDT: An Efficient and Effective Fully Transformer-based Object Detector
Transformers are transforming the landscape of computer vision, especially for recognition tasks.
Ranked #11 on
Object Detection
on COCO 2017 val
Burst Image Restoration and Enhancement
Our central idea is to create a set of pseudo-burst features that combine complementary information from all the input burst frames to seamlessly exchange information.
Ranked #2 on
Burst Image Super-Resolution
on BurstSR
Learning Contrastive Representation for Semantic Correspondence
Dense correspondence across semantically related images has been extensively studied, but still faces two challenges: 1) large variations in appearance, scale and pose exist even for objects from the same category, and 2) labeling pixel-level dense correspondences is labor intensive and infeasible to scale.
Federated Multi-Target Domain Adaptation
We further take the server-client and inter-client domain shifts into account and pose a domain adaptation problem with one source (centralized server data) and multiple targets (distributed client data).
Discovering 3D Parts from Image Collections
Reasoning 3D shapes from 2D images is an essential yet challenging task, especially when only single-view images are at our disposal.
End-to-end Multi-modal Video Temporal Grounding
Specifically, we adopt RGB images for appearance, optical flow for motion, and depth maps for image structure.
Learning 3D Dense Correspondence via Canonical Point Autoencoder
We propose a canonical point autoencoder (CPAE) that predicts dense correspondences between 3D shapes of the same category.
Self-Supervised Tracking via Target-Aware Data Synthesis
While deep-learning based tracking methods have achieved substantial progress, they entail large-scale and high-quality annotated data for sufficient training.
Incremental False Negative Detection for Contrastive Learning
Self-supervised learning has recently shown great potential in vision tasks through contrastive learning, which aims to discriminate each image, or instance, in the dataset.
Large-scale Unsupervised Semantic Segmentation
In this work, we propose a new problem of large-scale unsupervised semantic segmentation (LUSS) with a newly created benchmark dataset to help the research progress.
Ranked #1 on
Unsupervised Semantic Segmentation
on ImageNet-S-50
Learning to Stylize Novel Views
Second, we develop point cloud aggregation modules to gather the style information of the 3D scene, and then modulate the features in the point cloud with a linear transformation matrix.
Intriguing Properties of Vision Transformers
We show and analyze the following intriguing properties of ViT: (a) Transformers are highly robust to severe occlusions, perturbations and domain shifts, e. g., retain as high as 60% top-1 accuracy on ImageNet even after randomly occluding 80% of the image content.
COMISR: Compression-Informed Video Super-Resolution
Most video super-resolution methods focus on restoring high-resolution video frames from low-resolution videos without taking into account compression.
Decoupled Dynamic Filter Networks
Inspired by recent advances in attention, DDF decouples a depth-wise dynamic filter into spatial and channel dynamic filters.
Ranked #4 on
Semantic Segmentation
on MCubeS
2.5D Visual Relationship Detection
To enable progress on this task, we create a new dataset consisting of 220k human-annotated 2. 5D relationships among 512K objects from 11K images.
Understanding Synonymous Referring Expressions via Contrastive Features
While prior work usually treats each sentence and attends it to an object separately, we focus on learning a referring expression comprehension model that considers the property in synonymous sentences.
Weakly Supervised Object Localization and Detection: A Survey
As an emerging and challenging problem in the computer vision community, weakly supervised object localization and detection plays an important role for developing new generation computer vision systems and has received significant attention in the past decade.
The Road to Know-Where: An Object-and-Room Informed Sequential BERT for Indoor Vision-Language Navigation
Vision-and-Language Navigation (VLN) requires an agent to find a path to a remote location on the basis of natural-language instructions and a set of photo-realistic panoramas.
InfinityGAN: Towards Infinite-Pixel Image Synthesis
We present a novel framework, InfinityGAN, for arbitrary-sized image generation.
Regularizing Generative Adversarial Networks under Limited Data
Recent years have witnessed the rapid progress of generative adversarial networks (GANs).
Ranked #1 on
Image Generation
on 25% ImageNet 128x128
In&Out : Diverse Image Outpainting via GAN Inversion
Existing image outpainting methods pose the problem as a conditional image-to-image translation task, often generating repetitive structures and textures by replicating the content available in the input image.
Unsupervised Sound Localization via Iterative Contrastive Learning
Sound localization aims to find the source of the audio signal in the visual scene.
ReMix: Towards Image-to-Image Translation with Limited Data
We interpolate training samples at the feature level and propose a novel content loss based on the perceptual relations among samples.
Self-Attentive 3D Human Pose and Shape Estimation from Videos
The key insights of our method are two-fold.
Ranked #20 on
3D Human Pose Estimation
on MPI-INF-3DHP
Hybrid Neural Fusion for Full-frame Video Stabilization
Existing video stabilization methods often generate visible distortion or require aggressive cropping of frame boundaries, resulting in smaller field of views.
Multi-Stage Progressive Image Restoration
At each stage, we introduce a novel per-pixel adaptive design that leverages in-situ supervised attention to reweight the local features.
Ranked #4 on
Deblurring
on RSBlur
Exploiting Raw Images for Real-Scene Super-Resolution
In this paper, we study the problem of real-scene single image super-resolution to bridge the gap between synthetic data and real captured images.
Learning Spatial and Spatio-Temporal Pixel Aggregations for Image and Video Denoising
We present a spatial pixel aggregation network and learn the pixel sampling and averaging strategies for image denoising.
GAN Inversion: A Survey
GAN inversion aims to invert a given image back into the latent space of a pretrained GAN model, for the image to be faithfully reconstructed from the inverted code by the generator.
Low Light Image Enhancement via Global and Local Context Modeling
These contexts can be crucial towards inferring several image enhancement tasks, e. g., local and global contrast, brightness and color corrections; which requires cues from both local and global spatial extent.
Benchmarking Ultra-High-Definition Image Super-Resolution
Increasingly, modern mobile devices allow capturing images at Ultra-High-Definition (UHD) resolution, which includes 4K and 8K images.
Video Matting via Consistency-Regularized Graph Neural Networks
In this paper, we propose to enhance the temporal coherence by Consistency-Regularized Graph Neural Networks (CRGNN) with the aid of a synthesized video matting dataset.
D2-Net: Weakly-Supervised Action Localization via Discriminative Embeddings and Denoised Activations
The proposed formulation comprises a discriminative and a denoising loss term for enhancing temporal action localization.
Ranked #3 on
Weakly Supervised Action Localization
on THUMOS’14
Online Adaptation for Consistent Mesh Reconstruction in the Wild
This paper presents an algorithm to reconstruct temporally consistent 3D meshes of deformable object instances from videos in the wild.
Unsupervised Discovery of Disentangled Manifolds in GANs
Interpretable generation process is beneficial to various image editing applications.
Shaping Deep Feature Space towards Gaussian Mixture for Visual Classification
In this work, we propose a Gaussian mixture (GM) loss function for deep neural networks for visual classification.
Continuous and Diverse Image-to-Image Translation via Signed Attribute Vectors
Generating a smooth sequence of intermediate results bridges the gap of two different domains, facilitating the morphing effect across domains.
Unsupervised Domain Adaptation for Spatio-Temporal Action Localization
Spatio-temporal action localization is an important problem in computer vision that involves detecting where and when activities occur, and therefore requires modeling of both spatial and temporal features.
Multi-path Neural Networks for On-device Multi-domain Visual Classification
This approach effectively reduces the total number of parameters and FLOPS, encouraging positive knowledge transfer while mitigating negative interference across domains.
Every Pixel Matters: Center-aware Feature Alignment for Domain Adaptive Object Detector
A domain adaptive object detector aims to adapt itself to unseen domains that may contain variations of object appearance, viewpoints or backgrounds.
SoDA: Multi-Object Tracking with Soft Data Association
Robust multi-object tracking (MOT) is a prerequisite fora safe deployment of self-driving cars.
Learning to Caricature via Semantic Shape Transform
Caricature is an artistic drawing created to abstract or exaggerate facial features of a person.
Learning to See Through Obstructions with Layered Decomposition
We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions, or adherent raindrops, from a short sequence of images captured by a moving camera.
Spatiotemporal Contrastive Video Representation Learning
Our representations are learned using a contrastive loss, where two augmented clips from the same short video are pulled together in the embedding space, while clips from different videos are pushed away.
Ranked #1 on
Self-Supervised Action Recognition
on Kinetics-600
Mixup-CAM: Weakly-supervised Semantic Segmentation via Uncertainty Regularization
Obtaining object response maps is one important step to achieve weakly-supervised semantic segmentation using image-level labels.
Weakly-Supervised Semantic Segmentation via Sub-category Exploration
Existing weakly-supervised semantic segmentation methods using image-level annotations typically rely on initial responses to locate object regions.
Learnable Cost Volume Using the Cayley Representation
Cost volume is an essential component of recent deep models for optical flow estimation and is usually constructed by calculating the inner product between two feature vectors.
RetrieveGAN: Image Synthesis via Differentiable Patch Retrieval
Image generation from scene description is a cornerstone technique for the controlled generation, which is beneficial to applications such as content creation and image editing.
Controllable Image Synthesis via SegVAE
We also apply an off-the-shelf image-to-image translation model to generate realistic RGB images to better understand the quality of the synthesized semantic maps.
Modeling Artistic Workflows for Image Generation and Editing
People often create art by following an artistic workflow involving multiple stages that inform the overall design.
Semi-Supervised Learning with Meta-Gradient
In this work, we propose a simple yet effective meta-learning algorithm in semi-supervised learning.
Ventral-Dorsal Neural Networks: Object Detection via Selective Attention
The coarse functional distinction between these streams is between object recognition -- the "what" of the signal -- and extracting location related information -- the "where" of the signal.
WW-Nets: Dual Neural Networks for Object Detection
Inspired by this structure, we have proposed an object detection framework involving the integration of a "What Network" and a "Where Network".
Generalized Convolutional Forest Networks for Domain Generalization and Visual Recognition
When constructing random forests, it is of prime importance to ensure high accuracy and low correlation of individual tree classifiers for good performance.
Multi-Scale Boosted Dehazing Network with Dense Feature Fusion
To address the issue of preserving spatial information in the U-Net architecture, we design a dense feature fusion module using the back-projection feedback scheme.
Ranked #8 on
Image Dehazing
on Haze4k
Regularizing Meta-Learning via Gradient Dropout
With the growing attention on learning-to-learn new tasks using only a few examples, meta-learning has been widely used in numerous problems such as few-shot classification, reinforcement learning, and domain generalization.
Single-Image HDR Reconstruction by Learning to Reverse the Camera Pipeline
We model the HDRto-LDR image formation pipeline as the (1) dynamic range clipping, (2) non-linear mapping from a camera response function, and (3) quantization.
Learning to See Through Obstructions
We present a learning-based approach for removing unwanted obstructions, such as window reflections, fence occlusions or raindrops, from a short sequence of images captured by a moving camera.
Deep Semantic Matching with Foreground Detection and Cycle-Consistency
Establishing dense semantic correspondences between object instances remains a challenging problem due to background clutter, significant scale and pose differences, and large intra-class variations.
TapLab: A Fast Framework for Semantic Video Segmentation Tapping into Compressed-Domain Knowledge
Real-time semantic video segmentation is a challenging task due to the strict requirements of inference speed.
Rethinking Class-Balanced Methods for Long-Tailed Visual Recognition from a Domain Adaptation Perspective
Object frequency in the real world often follows a power law, leading to a mismatch between datasets with long-tailed class distributions seen by a machine learning model and our expectation of the model to perform well on all classes.
Ranked #27 on
Long-tail Learning
on Places-LT
Collaborative Distillation for Ultra-Resolution Universal Style Transfer
In this work, we present a new knowledge distillation method (named Collaborative Distillation) for encoder-decoder based neural style transfer to reduce the convolutional filters.
CycleISP: Real Image Restoration via Improved Data Synthesis
This is mainly because the AWGN is not adequate for modeling the real camera noise which is signal-dependent and heavily transformed by the camera imaging pipeline.
Ranked #9 on
Image Denoising
on DND
(using extra training data)
Learning Enriched Features for Real Image Restoration and Enhancement
With the goal of recovering high-quality image content from its degraded version, image restoration enjoys numerous applications, such as in surveillance, computational photography, medical imaging, and remote sensing.
Ranked #4 on
Image Denoising
on DND
Self-supervised Single-view 3D Reconstruction via Semantic Consistency
To the best of our knowledge, we are the first to try and solve the single-view reconstruction problem without a category-specific template mesh or semantic keypoints.
Gated Fusion Network for Degraded Image Super Resolution
To address this problem, we propose a dual-branch convolutional neural network to extract base features and recovered features separately.
Structured Sparsification with Joint Optimization of Group Convolution and Channel Shuffle
Recent advances in convolutional neural networks(CNNs) usually come with the expense of excessive computational overhead and memory footprint.
Weakly-Supervised Semantic Segmentation by Iterative Affinity Learning
In this paper, we propose an iterative algorithm to learn such pairwise relations, which consists of two branches, a unary segmentation network which learns the label probabilities for each pixel, and a pairwise affinity network which learns affinity matrix and refines the probability map generated from the unary network.
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Cross-Domain Few-Shot Classification via Learned Feature-Wise Transformation
Few-shot classification aims to recognize novel categories with only few labeled images in each class.
Exploiting Semantics for Face Image Deblurring
Specifically, we first use a coarse deblurring network to reduce the motion blur on the input face image.
Visual Question Answering on 360° Images
We then study two different VQA models on VQA 360, including one conventional model that takes an equirectangular image (with intrinsic distortion) as input and one dedicated model that first projects a 360 image onto cubemaps and subsequently aggregates the information from multiple spatial resolutions.
CrDoCo: Pixel-level Domain Transfer with Cross-Domain Consistency
Unsupervised domain adaptation algorithms aim to transfer the knowledge learned from one domain to another (e. g., synthetic to real images).
RC-DARTS: Resource Constrained Differentiable Architecture Search
In this paper, we propose the resource constrained differentiable architecture search (RC-DARTS) method to learn architectures that are significantly smaller and faster while achieving comparable accuracy.
Controllable and Progressive Image Extrapolation
Image extrapolation aims at expanding the narrow field of view of a given image patch.
Neural Design Network: Graphic Layout Generation with Constraints
The first module predicts a graph with complete relations from a graph with user-specified relations.
Adversarial Learning of Privacy-Preserving and Task-Oriented Representations
For instance, there could be a potential privacy risk of machine learning systems via the model inversion attack, whose goal is to reconstruct the input data from the latent representation of deep networks.
Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications
Visual events are usually accompanied by sounds in our daily lives.
Dancing to Music
In the analysis phase, we decompose a dance into a series of basic dance units, through which the model learns how to move.
Ranked #3 on
Motion Synthesis
on BRACE
Quadratic video interpolation
Video interpolation is an important problem in computer vision, which helps overcome the temporal limitation of camera sensors.
Progressive Domain Adaptation for Object Detection
This intermediate domain is constructed by translating the source images to mimic the ones in the target domain.
Referring Expression Object Segmentation with Caption-Aware Consistency
To this end, we propose an end-to-end trainable comprehension network that consists of the language and visual encoders to extract feature representations from both domains.
Ranked #15 on
Referring Expression Segmentation
on RefCoCo val
