![Loading...](https://link.springer.com/static/c4a417b97a76cc2980e3c25e2271af3129e08bbe/images/pdf-preview/spacer.gif)
717 Result(s)
-
Article
Hugs Bring Double Benefits: Unsupervised Cross-Modal Hashing with Multi-granularity Aligned Transformers
Unsupervised cross-modal hashing (UCMH) has been commonly explored to support large-scale cross-modal retrieval of unlabeled data. Despite promising progress, most existing approaches are developed on convolut...
-
Article
Softmax-Free Linear Transformers
Vision transformers (ViTs) have pushed the state-of-the-art for visual perception tasks. The self-attention mechanism underpinning the strength of ViTs has a quadratic complexity in both computation and memory...
-
Article
Does Confusion Really Hurt Novel Class Discovery?
When sampling data of specific classes (i.e., known classes) for a scientific task, collectors may encounter unknown classes (i.e., novel classes). Since these novel classes might be valuable for future research,...
-
Article
A full-detection association tracker with confidence optimization for real-time multi-object tracking
Multi-object tracking (MOT) aims to obtain trajectories with unique identifiers for multiple objects in a video stream. In current approaches, confidence thresholds were frequently used to perform multi-stage ...
-
Article
MFMANet: a multispectral pedestrian detection network using multi-resolution RGB feature reuse with multi-scale FIR attentions
In the realm of multispectral pedestrian detection, especially under challenging low-illumination, the existing methods, characterized by cross-modality feature interaction, lack generalization and are hard to...
-
Article
Diff-Font: Diffusion Model for Robust One-Shot Font Generation
Font generation presents a significant challenge due to the intricate details needed, especially for languages with complex ideograms and numerous characters, such as Chinese and Korean. Although various few-s...
-
Article
A hardware-friendly logarithmic quantization method for CNNs and FPGA implementation
Convolutional Neural Networks (CNNs) have been widely used in various fields due to their high accuracy and efficiency. The performance of CNNs is mainly affected by the computing capability, memory bandwidth,...
-
Article
Grounded Affordance from Exocentric View
Affordance grounding aims to locate objects’ “action possibilities” regions, an essential step toward embodied intelligence. Due to the diversity of interactive affordance, i.e., the uniqueness of different indiv...
-
Article
Delving into Identify-Emphasize Paradigm for Combating Unknown Bias
Dataset biases are notoriously detrimental to model robustness and generalization. The identify-emphasize paradigm appears to be effective in dealing with unknown biases. However, we discover that it is still ...
-
Article
Towards Defending Multiple \(\ell _p\) -Norm Bounded Adversarial Perturbations via Gated Batch Normalization
There has been extensive evidence demonstrating that deep neural networks are vulnerable to adversarial examples, which motivates the development of defenses against adversarial attacks. Existing adversarial d...
-
Article
EEA-Net: edge-enhanced assistance network for infrared small target detection
With the development of deep learning, the performance of infrared small target detection (IRSTD) has been significantly improved. A precise shape of the target edge is crucial for segmenting small infrared ta...
-
Article
GridFormer: Residual Dense Transformer with Grid Structure for Image Restoration in Adverse Weather Conditions
Image restoration in adverse weather conditions is a difficult task in computer vision. In this paper, we propose a novel transformer-based framework called GridFormer which serves as a backbone for image rest...
-
Article
Residual feature learning with hierarchical calibration for gaze estimation
Gaze estimation aims to predict accurate gaze direction from natural eye images, which is an extreme challenging task due to both random variations in head pose and person-specific biases. Existing works often...
-
Article
Convex–Concave Tensor Robust Principal Component Analysis
Tensor robust principal component analysis (TRPCA) aims at recovering the underlying low-rank clean tensor and residual sparse component from the observed tensor. The recovery quality heavily depends on the de...
-
Article
Diagram Perception Networks for Textbook Question Answering via Joint Optimization
Textbook question answering requires a system to answer questions with or without diagrams accurately, given multimodal contexts that include rich paragraphs and diagrams. Existing methods usually utilize a pi...
-
Article
Robust Unpaired Image Dehazing via Density and Depth Decomposition
To overcome the overfitting issue of dehazing models trained on synthetic hazy-clean image pairs, recent methods attempt to boost the generalization ability by training on unpaired data. However, most of exist...
-
Article
VNAS: Variational Neural Architecture Search
Differentiable neural architecture search delivers point estimation to the optimal architecture, which yields arbitrarily high confidence to the learned architecture. This approach thus suffers in calibration ...
-
Article
EATFormer: Improving Vision Transformer Inspired by Evolutionary Algorithm
Motivated by biological evolution, this paper explains the rationality of Vision Transformer by analogy with the proven practical evolutionary algorithm (EA) and derives that both have consistent mathematical ...
-
Article
MMoT: Mixture-of-Modality-Tokens Transformer for Composed Multimodal Conditional Image Synthesis
Existing multimodal conditional image synthesis (MCIS) methods generate images conditioned on any combinations of various modalities that require all of them must be exactly conformed, hindering the synthesis ...
-
Article
MixStyle Neural Networks for Domain Generalization and Adaptation
Neural networks do not generalize well to unseen data with domain shifts—a longstanding problem in machine learning and AI. To overcome the problem, we propose MixStyle, a simple plug-and-play, parameter-free ...