Search Results for author:
Found 94 papers, 58 papers with code
CLNet: A Compact Latent Network for Fast Adjusting Siamese Trackers
To make full use of these sequence-specific samples, {we propose a compact latent network to quickly adjust the tracking model to adapt to new scenes.}
High-Precision Self-Supervised Monocular Depth Estimation with Rich-Resource Prior
In the area of self-supervised monocular depth estimation, models that utilize rich-resource inputs, such as high-resolution and multi-frame inputs, typically achieve better performance than models that use ordinary single image input.
RepVF: A Unified Vector Fields Representation for Multi-task 3D Perception
Concurrent processing of multiple autonomous driving 3D perception tasks within the same spatiotemporal scene poses a significant challenge, in particular due to the computational inefficiencies and feature competition between tasks when using traditional multi-task learning approaches.
Ranked #4 on
3D Lane Detection
on OpenLane
AdaOcc: Adaptive Forward View Transformation and Flow Modeling for 3D Occupancy and Flow Prediction
In this technical report, we present our solution for the Vision-Centric 3D Occupancy and Flow Prediction track in the nuScenes Open-Occ Dataset Challenge at CVPR 2024.
Multi-threshold Deep Metric Learning for Facial Expression Recognition
Each embedding slice corresponds to a sample threshold and is learned by enforcing the corresponding triplet loss, yielding a set of distinct expression features, one for each embedding slice.
Facial Expression Recognition
Facial Expression Recognition (FER)
+2
Is a 3D-Tokenized LLM the Key to Reliable Autonomous Driving?
Despite its simplicity, Atlas demonstrates superior performance in both 3D detection and ego planning tasks on nuScenes dataset, proving that 3D-tokenized LLM is the key to reliable autonomous driving.
IS-Fusion: Instance-Scene Collaborative Fusion for Multimodal 3D Object Detection
HSF applies Point-to-Grid and Grid-to-Region transformers to capture the multimodal scene context at different granularities.
Visual In-Context Learning for Large Vision-Language Models
In Large Visual Language Models (LVLMs), the efficacy of In-Context Learning (ICL) remains limited by challenges in cross-modal interactions and representation disparities.
DME-Driver: Integrating Human Decision Logic and 3D Scene Perception in Autonomous Driving
On the other hand, the generation of accurate control signals relies on precise and detailed environmental perception, which is where 3D scene perception models excel.
Leveraging Frame Affinity for sRGB-to-RAW Video De-rendering
These methods utilize both the metadata and the sRGB image to perform sRGB-to-RAW de-rendering and recover high-quality single-frame RAW data.
DI-V2X: Learning Domain-Invariant Representation for Vehicle-Infrastructure Collaborative 3D Object Detection
Specifically, DMA builds a domain-mixing 3D instance bank for the teacher and student models during training, resulting in aligned data representation.
Thread of Thought Unraveling Chaotic Contexts
Large Language Models (LLMs) have ushered in a transformative era in the field of natural language processing, excelling in tasks related to text comprehension and generation.
TopoMLP: A Simple yet Strong Pipeline for Driving Topology Reasoning
Further, we propose TopoMLP, a simple yet high-performance pipeline for driving topology reasoning.
Ranked #3 on
3D Lane Detection
on OpenLane-V2 val
Decoupling the Curve Modeling and Pavement Regression for Lane Detection
The curve-based lane representation is a popular approach in many lane detection methods, as it allows for the representation of lanes as a whole object and maximizes the use of holistic information about the lanes.
Language Prompt for Autonomous Driving
A new trend in the computer vision community is to capture objects of interest following flexible human command represented by a natural language prompt.
Self-Supervised Monocular Depth Estimation by Direction-aware Cumulative Convolution Network
To bridge this gap, we propose a new Direction-aware Cumulative Convolution Network (DaCCN), which improves the depth feature representation in two aspects.
Monocular Depth Estimation
Unsupervised Monocular Depth Estimation
OnlineRefer: A Simple Online Baseline for Referring Video Object Segmentation
Referring video object segmentation (RVOS) aims at segmenting an object in a video following human instruction.
Referring Expression Segmentation
Referring Video Object Segmentation
+2
TextFormer: A Query-based End-to-End Text Spotter with Mixed Supervision
End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified framework.
Language-Guided 3D Object Detection in Point Cloud for Autonomous Driving
In this work, we propose a new multi-modal visual grounding task, termed LiDAR Grounding.
Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency
When used as a pre-training method, our model can significantly outperform the corresponding fully-supervised baseline with only 1/3 3D labels.
Referring Multi-Object Tracking
In this paper, we propose a new and general referring understanding task, termed referring multi-object tracking (RMOT).
Generalized Few-Shot 3D Object Detection of LiDAR Point Cloud for Autonomous Driving
To achieve simultaneous detection for both common and rare objects, we propose a novel task, called generalized few-shot 3D object detection, where we have a large amount of training data for common (base) objects, but only a few data for rare (novel) classes.
Adaptive Siamese Tracking with a Compact Latent Network
Under this viewing, we perform an in-depth analysis for them through visual simulations and real tracking examples, and find that the failure cases in some challenging situations can be regarded as the issue of missing decisive samples in offline training.
LWSIS: LiDAR-guided Weakly Supervised Instance Segmentation for Autonomous Driving
In this paper, we present a more artful framework, LiDAR-guided Weakly Supervised Instance Segmentation (LWSIS), which leverages the off-the-shelf 3D data, i. e., Point Cloud, together with the 3D boxes, as natural weak supervisions for training the 2D image instance segmentation models.
SSDA3D: Semi-supervised Domain Adaptation for 3D Object Detection from Point Cloud
However, these UDA solutions just yield unsatisfactory 3D detection results when there is a severe domain shift, e. g., from Waymo (64-beam) to nuScenes (32-beam).
Rethinking Clustering-Based Pseudo-Labeling for Unsupervised Meta-Learning
In this work, we prove that the core reason for this is lack of a clustering-friendly property in the embedding space.
Semi-supervised 3D Object Detection with Proficient Teachers
To reduce the dependence on large supervision, semi-supervised learning (SSL) based approaches have been proposed.
ProposalContrast: Unsupervised Pre-training for LiDAR-based 3D Object Detection
Existing approaches for unsupervised point cloud pre-training are constrained to either scene-level or point/voxel-level instance discrimination.
Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i. e., the point cloud videos.
Counterfactual Cycle-Consistent Learning for Instruction Following and Generation in Vision-Language Navigation
Since the rise of vision-language navigation (VLN), great progress has been made in instruction following -- building a follower to navigate environments under the guidance of instructions.
Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation
The tree energy loss is effective and easy to be incorporated into existing frameworks by combining it with a traditional segmentation loss.
Consistency and Diversity induced Human Motion Segmentation
Besides, a novel constraint based on the Hilbert Schmidt Independence Criterion (HSIC) is introduced to ensure the diversity of multi-level subspace representations, which enables the complementarity of multi-level representations to be explored to boost the transfer learning performance.
A Graph Matching Perspective With Transformers on Video Instance Segmentation
Video Instance Segmentation (VIS) needs to automatically track and segment multiple objects in videos that rely on modeling the spatial-temporal interactions of the instances.
Multi-Level Representation Learning With Semantic Alignment for Referring Video Object Segmentation
To address this, we propose a novel multi-level representation learning approach, which explores the inherent structure of the video content to provide a set of discriminative visual embedding, enabling more effective vision-language semantic alignment.
Bilateral Cross-Modality Graph Matching Attention for Feature Fusion in Visual Question Answering
In this paper, we focus on these two problems and propose a Graph Matching Attention (GMA) network.
Full-Duplex Strategy for Video Object Segmentation
Previous video object segmentation approaches mainly focus on using simplex solutions between appearance and motion, limiting feature collaboration efficiency among and across these two cues.
Ranked #9 on
Video Polyp Segmentation
on SUN-SEG-Hard (Unseen)
Person Re-Identification by Context-aware Part Attention and Multi-Head Collaborative Learning
In addition, we propose a novel multi-head collaborative training scheme to improve the performance, which is collaboratively supervised by multiple heads with the same structure but different parameters.
Face Forensics in the Wild
On existing public benchmarks, face forgery detection techniques have achieved great success.
Structured Scene Memory for Vision-Language Navigation
Recently, numerous algorithms have been developed to tackle the problem of vision-language navigation (VLN), i. e., entailing an agent to navigate 3D environments through following linguistic instructions.
Cross-Modality Person Re-Identification via Modality Confusion and Center Aggregation
Cross-modality person re-identification is a challenging task due to large cross-modality discrepancy and intra-modality variations.
Learning to Fuse Asymmetric Feature Maps in Siamese Trackers
We propose a learnable module, called the asymmetric convolution (ACM), which learns to better capture the semantic correlation information in offline training on large-scale data.
Ranked #24 on
Visual Object Tracking
on TrackingNet
Siamese Network for RGB-D Salient Object Detection and Beyond
Inspired by the observation that RGB and depth modalities actually present certain commonality in distinguishing salient objects, a novel joint learning and densely cooperative fusion (JL-DCF) architecture is designed to learn from both RGB and depth inputs through a shared network backbone, known as the Siamese architecture.
Ranked #3 on
RGB-D Salient Object Detection
on STERE
Weakly Supervised 3D Object Detection from Lidar Point Cloud
This work proposes a weakly supervised approach for 3D object detection, only requiring a small set of weakly annotated scenes, associated with a few precisely labeled object instances.
Dynamic Dual-Attentive Aggregation Learning for Visible-Infrared Person Re-Identification
In this paper, we propose a novel dynamic dual-attentive aggregation (DDAG) learning method by mining both intra-modality part-level and cross-modality graph-level contextual cues for VI-ReID.
Active Visual Information Gathering for Vision-Language Navigation
Vision-language navigation (VLN) is the task of entailing an agent to carry out navigational instructions inside photo-realistic environments.
Video Object Segmentation with Episodic Graph Memory Networks
How to make a segmentation model efficiently adapt to a specific video and to online target appearance variations are fundamentally crucial issues in the field of video object segmentation.
Re-thinking Co-Salient Object Detection
CoSOD is an emerging and rapidly growing extension of salient object detection (SOD), which aims to detect the co-occurring salient objects in a group of images.
Ranked #7 on
Co-Salient Object Detection
on CoCA
PraNet: Parallel Reverse Attention Network for Polyp Segmentation
To address these challenges, we propose a parallel reverse attention network (PraNet) for accurate polyp segmentation in colonoscopy images.
Ranked #3 on
Camouflaged Object Segmentation
on PCOD_1200
M2Net: Multi-modal Multi-channel Network for Overall Survival Time Prediction of Brain Tumor Patients
Then, we use a modality-specific network to extract implicit and high-level features from different MR scans.
Modeling and Enhancing Low-quality Retinal Fundus Images
Retinal fundus images are widely used for the clinical screening and diagnosis of eye diseases.
Inf-Net: Automatic COVID-19 Lung Infection Segmentation from CT Images
Coronavirus Disease 2019 (COVID-19) spread globally in early 2020, causing the world to face an existential health crisis.
Self-Learning with Rectification Strategy for Human Parsing
For the global error, we first transform category-wise features into a high-level graph model with coarse-grained structural information, and then decouple the high-level graph to reconstruct the category features.
LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
In this paper, we propose an end-to-end online 3D video object detector that operates on point cloud sequences.
A Unified Object Motion and Affinity Model for Online Multi-Object Tracking
In this paper, we propose a novel MOT framework that unifies object motion and affinity model into a single network, named UMA, in order to learn a compact feature that is discriminative for both object motion and affinity measure.
Hierarchical Human Parsing with Typed Part-Relation Reasoning
As human bodies are underlying hierarchically structured, how to model human structures is the central theme in this task.
Learning Video Object Segmentation from Unlabeled Videos
We propose a new method for video object segmentation (VOS) that addresses object pattern learning from unlabeled videos, unlike most existing methods which rely heavily on extensive annotated data.
Cascaded Human-Object Interaction Recognition
The interaction recognition network has two crucial parts: a relation ranking module for high-quality HOI proposal selection and a triple-stream classifier for relation prediction.
Infinitely Wide Graph Convolutional Networks: Semi-supervised Learning via Gaussian Processes
Graph convolutional neural networks~(GCNs) have recently demonstrated promising results on graph-based semi-supervised classification, but little work has been done to explore their theoretical properties.
Hi-Net: Hybrid-fusion Network for Multi-modal MR Image Synthesis
Medical image synthesis has been proposed as an effective solution to this, where any missing modalities are synthesized from the existing ones.
Learning Compositional Neural Information Fusion for Human Parsing
The bottom-up and top-down inferences explicitly model the compositional and decompositional relations in human bodies, respectively.
See More, Know More: Unsupervised Video Object Segmentation with Co-Attention Siamese Networks
We introduce a novel network, called CO-attention Siamese Network (COSNet), to address the unsupervised video object segmentation task from a holistic view.
Ranked #11 on
Video Polyp Segmentation
on SUN-SEG-Hard (Unseen)
Semantic Segmentation
Unsupervised Video Object Segmentation
+2
Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
Through parametric message passing, AGNN is able to efficiently capture and mine much richer and higher-order relations between video frames, thus enabling a more complete understanding of video content and more accurate foreground estimation.
Human-Aware Motion Deblurring
This paper proposes a human-aware deblurring model that disentangles the motion blur between foreground (FG) humans and background (BG).
NETNet: Neighbor Erasing and Transferring Network for Better Single Shot Object Detection
With this observation, we propose a new Neighbor Erasing and Transferring (NET) mechanism to reconfigure the pyramid features and explore scale-aware features.
Deep Learning for Person Re-identification: A Survey and Outlook
The widely studied closed-world setting is usually applied under various research-oriented assumptions, and has achieved inspiring success using deep learning techniques on a number of datasets.
Ranked #1 on
Cross-Modal Person Re-Identification
on RegDB-C
ET-Net: A Generic Edge-aTtention Guidance Network for Medical Image Segmentation
Segmentation is a fundamental task in medical image analysis.
Ranked #1 on
Optic Disc Segmentation
on REFUGE
Distilled Siamese Networks for Visual Tracking
This model is intuitively inspired by the one teacher vs. multiple students learning method typically employed in schools.
Evaluation of Retinal Image Quality Assessment Networks in Different Color-spaces
Retinal image quality assessment (RIQA) is essential for controlling the quality of retinal imaging and guaranteeing the reliability of diagnoses by ophthalmologists or automated analysis systems.
Understanding More about Human and Machine Attention in Deep Neural Networks
With three example computer vision tasks, diverse representative backbones, and famous architectures, corresponding real human gaze data, and systematically conducted large-scale quantitative studies, we quantify the consistency between artificial attention and human visual attention and offer novel insights into existing artificial attention mechanisms by giving preliminary answers to several key questions related to human and artificial attention mechanisms.
Extreme Points Derived Confidence Map as a Cue For Class-Agnostic Segmentation Using Deep Neural Network
To automate the process of segmenting an anatomy of interest, we can learn a model from previously annotated data.
Adversarial Defense by Restricting the Hidden Space of Deep Neural Networks
Deep neural networks are vulnerable to adversarial attacks, which can fool them by adding minuscule perturbations to the input images.
Ranked #7 on
Adversarial Defense
on CIFAR-10
Max-margin Class Imbalanced Learning with Gaussian Affinity
Real-world object classes appear in imbalanced ratios.
Striking the Right Balance with Uncertainty
Rare classes tend to get a concentrated representation in the classification space which hampers the generalization of learned boundaries to new test examples.
Image Super-Resolution as a Defense Against Adversarial Attacks
The proposed scheme is simple and has the following advantages: (1) it does not require any model training or parameter optimization, (2) it complements other existing defense mechanisms, (3) it is agnostic to the attacked model and attack type and (4) it provides superior performance across all popular attack algorithms.
Triplet Loss in Siamese Network for Object Tracking
In this paper, a novel triplet loss is proposed to extract expressive deep feature for object tracking by adding it into Siamese network framework instead of pairwise loss for training.
Pyramid Dilated Deeper ConvLSTM for Video Salient Object Detection
This paper proposes a fast video salient object detection model, based on a novel recurrent network architecture, named Pyramid Dilated Bidirectional ConvLSTM (PDB-ConvLSTM).
Ranked #1 on
Video Salient Object Detection
on UVSD
(using extra training data)
Learning Human-Object Interactions by Graph Parsing Neural Networks
For a given scene, GPNN infers a parse graph that includes i) the HOI graph structure represented by an adjacency matrix, and ii) the node labels.
Ranked #32 on
Human-Object Interaction Detection
on V-COCO
Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification
This paper proposes a knowledge-guided fashion network to solve the problem of visual fashion analysis, e. g., fashion landmark localization and clothing category classification.
Salient Object Detection Driven by Fixation Prediction
Salient object detection is then viewed as fine-grained object-level saliency segmentation and is progressively optimized with the guidance of the fixation map in a top-down manner.
Hyperparameter Optimization for Tracking With Continuous Deep Q-Learning
Hyperparameters are numerical presets whose values are assigned prior to the commencement of the learning process.
Revisiting Video Saliency: A Large-scale Benchmark and a New Model
Existing video saliency datasets lack variety and generality of common dynamic scenes and fall short in covering challenging situations in unconstrained environments.
Deep Cropping via Attention Box Prediction and Aesthetics Assessment
We model the photo cropping problem as a cascade of attention box regression and aesthetic quality classification, based on deep learning.
Improved Face Detection and Alignment using Cascade Deep Convolutional Network
Real-world face detection and alignment demand an advanced discriminative model to address challenges by pose, lighting and expression.
Quadruplet Network with One-Shot Learning for Fast Visual Object Tracking
In this paper, we propose a new quadruplet deep network to examine the potential connections among the training instances, aiming to achieve a more powerful representation.
Deep Visual Attention Prediction
Our model is based on a skip-layer network structure, which predicts human attention from multiple convolutional layers with various reception fields.
Selective Video Object Cutout
Conventional video segmentation approaches rely heavily on appearance models.
Super-Trajectory for Video Segmentation
We introduce a novel semi-supervised video segmentation approach based on an efficient video representation, called as "super-trajectory".
Video Salient Object Detection via Fully Convolutional Networks
This paper proposes a deep learning model to efficiently detect salient regions in videos.
Linearization to Nonlinear Learning for Visual Tracking
Building on the theory of globally linear approximations to nonlinear functions, we introduce an elegant method that jointly learns a nonlinear classifier and a visual dictionary for tracking objects in a semi-supervised sparse coding fashion.
Saliency-Aware Geodesic Video Object Segmentation
Building on the observation that foreground areas are surrounded by the regions with high spatiotemporal edge values, geodesic distance provides an initial estimation for foreground and background.
Ranked #5 on
Video Salient Object Detection
on DAVSOD-Difficult20
(using extra training data)
Lazy Random Walks for Superpixel Segmentation
Then, the boundaries of initial superpixels are obtained according to the probabilities and the commute time.
