Search Results for author:
Found 23 papers, 13 papers with code
GuardSplat: Efficient and Robust Watermarking for 3D Gaussian Splatting
Specifically, 1) We propose a CLIP-guided pipeline for optimizing the message decoder with minimal costs.
Progressive Pretext Task Learning for Human Trajectory Prediction
In the final stage, the model aims to address the entire future trajectory task by taking full advantage of the knowledge from previous stages.
Ranked #3 on
Trajectory Prediction
on Stanford Drone
View-decoupled Transformer for Person Re-identification under Aerial-ground Camera Network
Experiments on two datasets show that VDT is a feasible and effective solution for AGPReID, surpassing the previous method on mAP/Rank1 by up to 5. 0%/2. 7% on CARGO and 3. 7%/5. 2% on AG-ReID, keeping the same magnitude of computational complexity.
Ranked #1 on
Person Re-Identification
on AG-ReID
Siamese Learning with Joint Alignment and Regression for Weakly-Supervised Video Paragraph Grounding
Different from previous weakly-supervised grounding frameworks based on multiple instance learning or reconstruction learning for two-stage candidate ranking, we propose a novel siamese learning framework that jointly learns the cross-modal feature alignment and temporal coordinate regression without timestamp labels to achieve concise one-stage localization for WSVPG.
APRF: Anti-Aliasing Projection Representation Field for Inverse Problem in Imaging
However, these methods have not considered the correlation between adjacent projection views, resulting in aliasing artifacts on SV sinograms.
Hard-normal Example-aware Template Mutual Matching for Industrial Anomaly Detection
PTS selects cluster centres and hard-normal examples to preserve the original decision boundary, allowing this tiny set to achieve comparable performance to the original one.
Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challenges
Deep learning techniques have achieved superior performance in computer-aided medical image analysis, yet they are still vulnerable to imperceptible adversarial attacks, resulting in potential misdiagnosis in clinical practice.
Similarity Metric Learning for RGB-Infrared Group Re-Identification
In the weak-supervised case, we design the Relation-aware Module (RAM) that exploits visual context and relations among group members to produce a modality-invariant order of features in each group, with which group member features within a set can be sorted to form a robust group representation against modality change.
The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training
To circumvent this issue, we propose a novel adversarial training scheme that encourages the model to produce similar outputs for an adversarial example and its ``inverse adversarial'' counterpart.
Understanding Weight Similarity of Neural Networks via Chain Normalization Rule and Hypothesis-Training-Testing
We extend the traditional hypothesis-testing method to a hypothesis-training-testing statistical inference method to validate the hypothesis on the weight similarity of neural networks.
Texture-guided Saliency Distilling for Unsupervised Salient Object Detection
In this paper, we propose a novel USOD method to mine rich and accurate saliency knowledge from both easy and hard samples.
SNN2ANN: A Fast and Memory-Efficient Training Framework for Spiking Neural Networks
The SNN2ANN consists of 2 components: a) a weight sharing architecture between ANN and SNN and b) spiking mapping units.
Cross-Camera Trajectories Help Person Retrieval in a Camera Network
To address this issue, we propose a pedestrian retrieval framework based on cross-camera trajectory generation, which integrates both temporal and spatial information.
Restricted Black-box Adversarial Attack Against DeepFake Face Swapping
DeepFake face swapping presents a significant threat to online security and social media, which can replace the source face in an arbitrary photo/video with the target face of an entirely different person.
Self-supervised Image-specific Prototype Exploration for Weakly Supervised Semantic Segmentation
Weakly Supervised Semantic Segmentation (WSSS) based on image-level labels has attracted much attention due to low annotation costs.
Ranked #21 on
Weakly-Supervised Semantic Segmentation
on COCO 2014 val
Weakly supervised Semantic Segmentation
Weakly-Supervised Semantic Segmentation
Exploring Dual-task Correlation for Pose Guided Person Image Generation
Pose Guided Person Image Generation (PGPIG) is the task of transforming a person image from the source pose to a given target pose.
Benchmarking Deep Models for Salient Object Detection
In recent years, deep network-based methods have continuously refreshed state-of-the-art performance on Salient Object Detection (SOD) task.
Activation to Saliency: Forming High-Quality Labels for Completely Unsupervised Salient Object Detection
Moreover, a new loss function is proposed to facilitate the generation of high-quality pseudo labels.
Confidence-guided Adaptive Gate and Dual Differential Enhancement for Video Salient Object Detection
Video salient object detection (VSOD) aims to locate and segment the most attractive object by exploiting both spatial cues and temporal cues hidden in video sequences.
ASPCNet: A Deep Adaptive Spatial Pattern Capsule Network for Hyperspectral Image Classification
Based on this observation, this paper proposes an adaptive spatial pattern capsule network (ASPCNet) architecture by developing an adaptive spatial pattern (ASP) unit, that can rotate the sampling location of convolutional kernels on the basis of an enlarged receptive field.
Heterogeneous Model Transfer between Different Neural Networks
Specifically, we select the longest chain from the source model and transfer it to the longest chain of the target model.
Function Feature Learning of Neural Networks
We present a Function Feature Learning (FFL) method that can measure the similarity of non-convex neural networks.
