Search Results for author:
Found 39 papers, 16 papers with code
Boosting Gaze Object Prediction via Pixel-level Supervision from Vision Foundation Model
Gaze object prediction (GOP) aims to predict the category and location of the object that a human is looking at.
ProIn: Learning to Predict Trajectory Based on Progressive Interactions for Autonomous Driving
In this work, a progressive interaction network is proposed to enable the agent's feature to progressively focus on relevant maps, in order to better learn agents' feature representation capturing the relevant map constraints.
Defying Imbalanced Forgetting in Class Incremental Learning
This intriguing phenomenon, discovered in replay-based Class Incremental Learning (CIL), highlights the imbalanced forgetting of learned classes, as their accuracy is similar before the occurrence of catastrophic forgetting.
Towards HDR and HFR Video from Rolling-Mixed-Bit Spikings
However reconstructing HDR videos in high-speed conditions using single-bit spikings presents challenges due to the limited bit depth.
A Revisit of the Normalized Eight-Point Algorithm and A Self-Supervised Deep Solution
The normalized eight-point algorithm has been widely viewed as the cornerstone in two-view geometry computation, where the seminal Hartley's normalization has greatly improved the performance of the direct linear transformation algorithm.
Attention Weighted Local Descriptors
Local features detection and description are widely used in many vision applications with high industrial and commercial demands.
Free Lunch for Generating Effective Outlier Supervision
Generally, existing approaches in dealing with out-of-distribution (OOD) detection mainly focus on the statistical difference between the features of OOD and in-distribution (ID) data extracted by the classifiers.
Building Vision Transformers with Hierarchy Aware Feature Aggregation
Thanks to the excellent global modeling capability of attention mechanisms, the Vision Transformer has achieved better results than ConvNet in many computer tasks.
Joint Appearance and Motion Learning for Efficient Rolling Shutter Correction
Rolling shutter correction (RSC) is becoming increasingly popular for RS cameras that are widely used in commercial and industrial applications.
Searching Dense Point Correspondences via Permutation Matrix Learning
In response, this paper presents a novel end-to-end learning-based method to estimate the dense correspondence of 3D point clouds, in which the problem of point matching is formulated as a zero-one assignment problem to achieve a permutation matching matrix to implement the one-to-one principle fundamentally.
Learning a Task-specific Descriptor for Robust Matching of 3D Point Clouds
In this paper, we propose to learn a robust task-specific feature descriptor to consistently describe the correct point correspondence under interference.
Rolling Shutter Inversion: Bring Rolling Shutter Images to High Framerate Global Shutter Video
The RSSR is a very challenging task, and to our knowledge, no practical solution exists to date.
DSLA: Dynamic smooth label assignment for efficient anchor-free object detection
The dynamic smooth label is assigned to supervise the classification branch.
Context-Aware Video Reconstruction for Rolling Shutter Cameras
Then, a refinement scheme is proposed to guide the GS frame synthesis along with bilateral occlusion masks to produce high-fidelity GS video frames at arbitrary times.
VRNet: Learning the Rectified Virtual Corresponding Points for 3D Point Cloud Registration
3D point cloud registration is fragile to outliers, which are labeled as the points without corresponding points.
MTLDesc: Looking Wider to Describe Better
Limited by the locality of convolutional neural networks, most existing local features description methods only learn local descriptors with local information and lack awareness of global and surrounding spatial context.
Continual Stereo Matching of Continuous Driving Scenes With Growing Architecture
The deep stereo models have achieved state-of-the-art performance on driving scenes, but they suffer from severe performance degradation when tested on unseen scenes.
SUNet: Symmetric Undistortion Network for Rolling Shutter Correction
The vast majority of modern consumer-grade cameras employ a rolling shutter mechanism, leading to image distortions if the camera moves during image acquisition.
Inverting a Rolling Shutter Camera: Bring Rolling Shutter Images to High Framerate Global Shutter Video
In this paper, we propose to invert the above RS imaging mechanism, i. e., recovering a high framerate GS video from consecutive RS images to achieve RS temporal super-resolution (RSSR).
Search What You Want: Barrier Panelty NAS for Mixed Precision Quantization
Learning to find an optimal mixed precision model that can preserve accuracy and satisfy the specific constraints on model size and computation is extremely challenge due to the difficult in training a mixed precision model and the huge space of all possible bit quantizations.
Relative Pose Estimation for Stereo Rolling Shutter Cameras
In this paper, we present a novel linear algorithm to estimate the 6 DoF relative pose from consecutive frames of stereo rolling shutter (RS) cameras.
Deep Attention Aware Feature Learning for Person Re-Identification
Visual attention has proven to be effective in improving the performance of person re-identification.
Ranked #11 on
Person Re-Identification
on DukeMTMC-reID
AugFPN: Improving Multi-scale Feature Learning for Object Detection
In this paper, we begin by first analyzing the design defects of feature pyramid in FPN, and then introduce a new feature pyramid architecture named AugFPN to address these problems.
Guiding the Flowing of Semantics: Interpretable Video Captioning via POS Tag
To address these problems, we propose an Adaptive Semantic Guidance Network (ASGN), which instantiates the whole video semantics to different POS-aware semantics with the supervision of part of speech (POS) tag.
DensePoint: Learning Densely Contextual Representation for Efficient Point Cloud Processing
Point cloud processing is very challenging, as the diverse shapes formed by irregular points are often indistinguishable.
Ranked #23 on
3D Part Segmentation
on ShapeNet-Part
Relation-Shape Convolutional Neural Network for Point Cloud Analysis
Specifically, the convolutional weight for local point set is forced to learn a high-level relation expression from predefined geometric priors, between a sampled point from this point set and the others.
Ranked #11 on
3D Point Cloud Classification
on ModelNet40-C
SOSNet: Second Order Similarity Regularization for Local Descriptor Learning
Despite the fact that Second Order Similarity (SOS) has been used with significant success in tasks such as graph matching and clustering, it has not been exploited for learning local descriptors.
Progressive Sparse Local Attention for Video object detection
Instead of relying on optical flow, this paper proposes a novel module called Progressive Sparse Local Attention (PSLA), which establishes the spatial correspondence between features across frames in a local region with progressively sparser stride and uses the correspondence to propagate features.
Semantic Labeling in Very High Resolution Images via a Self-Cascaded Convolutional Neural Network
Specifically, for confusing manmade objects, ScasNet improves the labeling coherence with sequential global-to-local contexts aggregation.
A Performance Evaluation of Local Features for Image Based 3D Reconstruction
To obtain a comprehensive evaluation, we choose to include both float type features and binary ones.
L2-Net: Deep Learning of Discriminative Patch Descriptor in Euclidean Space
In this paper, we propose to learn high per- formance descriptor in Euclidean space via the Convolu- tional Neural Network (CNN).
Do We Need Binary Features for 3D Reconstruction?
Binary features have been incrementally popular in the past few years due to their low memory footprints and the efficient computation of Hamming distance between binary descriptors.
kNN Hashing With Factorized Neighborhood Representation
Hashing is very effective for many tasks in reducing the processing time and in compressing massive databases.
Beyond Mahalanobis Metric: Cayley-Klein Metric Learning
Experiments have shown the superiority of Cayley-Klein metric over Mahalanobis ones and the effectiveness of our Cayley-Klein metric learning methods.
10,000+ Times Accelerated Robust Subset Selection (ARSS)
Subset selection from massive data with noised information is increasingly popular for various applications.
Effective Spectral Unmixing via Robust Representation and Learning-based Sparsity
Based on this observation, we exploit a learning-based sparsity method to simultaneously learn the HU results and a sparse guidance map.
Affine Subspace Representation for Feature Description
This paper proposes a novel Affine Subspace Representation (ASR) descriptor to deal with affine distortions induced by viewpoint changes.
Structured Sparse Method for Hyperspectral Unmixing
With this constraint, our method can learn a compact space, where highly similar pixels are grouped to share correlated sparse representations.
Spectral Unmixing via Data-guided Sparsity
Hyperspectral unmixing, the process of estimating a common set of spectral bases and their corresponding composite percentages at each pixel, is an important task for hyperspectral analysis, visualization and understanding.
