Canada

Vignetting commonly occurs as a degradation in images resulting from factors such as lens design, improper lens hood usage, and limitations in camera sensors. This degradation affects image details, color accuracy, and presents challenges in computational photography. Existing vignetting removal algorithms predominantly rely on ideal physics assumptions and hand-crafted parameters, resulting in ineffective removal of irregular vignetting and suboptimal results. Moreover, the substantial lack of real-world vignetting datasets hinders the objective and comprehensive evaluation of vignetting removal. To address these challenges, we present Vigset, a pioneering dataset for vignette removal. Vigset includes 983 pairs of both vignetting and vignetting-free high-resolution ($5340\times3697$) real-world images under various conditions. In addition, We introduce DeVigNet, a novel frequency-aware Transformer architecture designed for vignetting removal. Through the Laplacian Pyramid decomposition, we propose the Dual Aggregated Fusion Transformer to handle global features and remove vignetting in the low-frequency domain. Additionally, we introduce the Adaptive Channel Expansion Module to enhance details in the high-frequency domain. The experiments demonstrate that the proposed model outperforms existing state-of-the-art methods.

AAAI 2024

Devignet: High-Resolution Vignetting Removal via a Dual Aggregated Fusion Transformer with Adaptive Channel Expansion

vignetting

low-level vision

computer vision

**General Chair Welcome**

![](https://assets.underline.io/markdown_image/1/image/d6e6dddc08bf2371b9136ea9c18dc5ab.png)              

Welcome to ICALEO® 2023!
	
We were excited to host the world’s leading international conference on Lasers and Electro-Optics in Chicago. The Laser has been shown to have the potential to revolutionize solutions for major global challenges like energy usage and supply, global warming, and CO2 footprint. Even the fusion energy breakthrough is based on laser technology. The conference, with peer-reviewed scientific and technical presentations, focused on the newest results in Micro Applications, Macro Applications, Additive Manufacturing, Beam Shaping and Frontiers in Laser Applications. Additionally, the Battery-Manufacturing Track gave an overview of the process combined with the newest advances in laser application results. 

The Business Session brought the business aspect and environment of the laser to the audience and the possibility to discuss with seasoned industry leaders from around the world. 

Whether this is the first time you are hearing about ICALEO or you are a longtime attendee, you will find something of interest, new ideas, and an excellent opportunity to network with other laser specialists worldwide. 

**Klaus Löffler **  
ICALEO General Chair   
Managing Director, Precitec GmbH

**What is ICALEO?**

ICALEO® brings together the brightest minds, seasoned professionals, and pioneering researchers from around the world. With a laser-focused agenda, ICALEO offers an exceptional platform to delve into the cutting-edge advancements, diverse applications, and transformative research that define lasers and electro-optics.

Participants will be immersed in a dynamic environment that fosters collaborative learning, networking, and idea exchange. Through engaging plenary presentations, technical sessions, an industry business panel, and networking events, attendees gain insights into the forefront of laser technology. From industrial applications to medical breakthroughs, additive manufacturing to materials processing, ICALEO covers the entire spectrum of laser-related disciplines. Moreover, the event serves as a launching pad for synergistic partnerships, paving the way for professionals to forge connections that shape the future of our industry.

Join us in Chicago and be part of an unparalleled gathering that challenges the boundaries of possibility within lasers and electro-optics. As we convene to share knowledge, explore innovations, and cultivate collaborations, ICALEO stands as a pivotal force driving the evolution of this transformative technology.

**Who attended?**

ICALEO is tailor-made for professionals, researchers, academics, and enthusiasts who are deeply passionate about the world of lasers and electro-optics. If you're an industry trailblazer, an academic luminary, an aspiring expert, or a postgraduate student looking to dive into the latest developments and trends, this is an event you won't want to miss.

Industrial leaders seeking to stay ahead of the curve in their fields, engineers working on laser applications, and manufacturing experts interested in additive manufacturing and materials processing will find ICALEO to be an invaluable platform. Researchers and scientists exploring the forefront of laser technology, from fundamental principles to groundbreaking applications, will also discover a wealth of knowledge and networking opportunities.

Medical professionals investigating laser-based medical advancements, entrepreneurs seeking to innovate with lasers, educators aiming to stay updated with the latest in laser education, and policy makers shaping the industry's landscape are all essential attendees. Whether you're an established expert or a rising star, the 42nd annual ICALEO promises to offer a diverse ecosystem of expertise, connections, and knowledge sharing that caters to the laser and electro-optics communities.

**Fields Represented:**

* Entrepreneurs and Innovators
* Manufacturing Experts
* Students and Graduates
* Policy Makers and Regulators
* Consultants and Advisors
* Technology Enthusiasts
* Suppliers and Manufacturers
* Startups and Innovators
* Researchers in Laser Education

**[View All Proceedings Here](https://icaleo.conferencespot.org/event-data)**

### **Program Tracks & Chairs**

To access the site please register [**here**](https://icaleo.org/attend). 

Please register for the ICALEO 2023 Conference to join the event.

ICALEO 2023

ICALEO® brings together the brightest minds, seasoned professionals, and pioneering researchers from around the world. With a laser-focused agenda, ICALEO offers an exceptional platform to delve into the cutting-edge advancements, diverse applications, and transformative research that define lasers and electro-optics.

technical paper

We are pleased to announce the Thirty-Eighth AAAI Conference on Artificial Intelligence (AAAI-24), which will be held in Vancouver, British Columbia at the Vancouver Convention Centre – West Building from 20-27 February, 2024.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-24 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

We expect for AAAI-24 to be an in-person conference – one author of all accepted papers will be expected to present work in person unless there are exceptional circumstances that prevent this.<br><br><br><br>

In order to access the AAAI-24 event page you need to register [here](https://aaai.org/aaai-conference/registration/)

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. 

Pioneering efforts have verified the effectiveness of the diffusion models in exploring the informative uncertainty for recommendation. Considering the difference between recommendation and image synthesis tasks, existing methods have undertaken tailored refinements to the diffusion and reverse process. However, these approaches typically use the highest-score item in corpus for user interest prediction, leading to the ignorance of the user's generalized preference contained within other items, thereby remaining constrained by the data sparsity issue. To address this issue, this paper presents a novel Plug-in Diffusion Model for Recommendation (PDRec) framework, which employs the diffusion model as a flexible plugin to jointly take full advantage of the diffusion-generating user preferences on all items. Specifically, PDRec first infers the users' dynamic preferences on all items via a time-interval diffusion model and proposes a Historical Behavior Reweighting (HBR) mechanism to identify the high-quality behaviors and suppress noisy behaviors. In addition to the observed items, PDRec proposes a Diffusion-based Positive Augmentation (DPA) strategy to leverage the top-ranked unobserved items as the potential positive samples, bringing in informative and diverse soft signals to alleviate data sparsity. To alleviate the false negative sampling issue, PDRec employs Noise-free Negative Sampling (NNS) to select stable negative samples for ensuring effective model optimization. Extensive experiments and analyses on four datasets have verified the superiority of the proposed PDRec over the state-of-the-art baselines and showcased the universality of PDRec as a flexible plugin for commonly-used sequential encoders in different recommendation scenarios. The code is available in https://github.com/hulkima/PDRec.

Plug-In Diffusion Model for Sequential Recommendation

Novel-view synthesis with sparse input views is important for real-world applications like AR/VR and autonomous driving. Recent methods have integrated depth information into NeRFs for sparse input synthesis, leveraging depth prior for geometric and spatial understanding. However, most existing works tend to overlook inaccuracies within depth maps and have low time efficiency. To address these issues, we propose a depth-guided robust and fast point cloud fusion NeRF for sparse inputs. We perceive radiance fields as an explicit voxel grid of features. A point cloud is constructed for each input view, characterized within the voxel grid using matrices and vectors. We accumulate the point cloud of each input view to construct the fused point cloud of the entire scene. Each voxel determines its density and appearance by referring to the point cloud of the entire scene. Through point cloud fusion and voxel grid fine-tuning, inaccuracies in depth values are refined or substituted by those from other views. Moreover, our method can achieve faster reconstruction and greater compactness through effective vector-matrix decomposition. Experimental results underline the superior performance and time efficiency of our approach compared to state-of-the-art baselines.

Depth-Guided Robust and Fast Point Cloud Fusion NeRF for Sparse Input Views

Temporal difference learning (TD) is a foundational concept in reinforcement learning (RL), aimed at efficiently assessing a policy's value function. TD(λ), a potent variant, incorporates a memory trace to distribute the prediction error into the historical context. However, this approach often neglects the significance of historical states and the relative importance of propagating the TD error, influenced by challenges such as visitation imbalance or outcome noise. To address this, we propose a novel TD algorithm named discerning TD learning (DTD), which allows flexible emphasis functions—predetermined or adapted during training—to allocate efforts effectively across states. We establish the convergence properties of our method within a specific class of emphasis functions and showcase its promising potential for adaptation to deep RL contexts. Empirical results underscore that employing a judicious emphasis function not only improves value estimation but also expedites learning across diverse scenarios.

Discerning Temporal Difference Learning

Multi-objective reinforcement learning (MORL) provides an effective solution for decision-making problems involving conflicting objectives. However, achieving high-quality approximations to the Pareto policy set remains challenging, especially in complex tasks with continuous or high-dimensional state-action space. In this paper, we propose the Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement Learning (PA2D-MORL) method, which constructs an efficient scheme for multi-objective problem decomposition and policy improvement, leading to a superior approximation of Pareto policy set. The proposed method leverages Pareto ascent direction to select the scalarization weights and computes the multi-objective policy gradient, which determines the policy optimization direction and ensures joint improvement on all objectives. Meanwhile, multiple policies are selectively optimized under an evolutionary framework to approximate the Pareto frontier from different directions. Additionally, a Pareto adaptive fine-tuning approach is applied to enhance the density and spread of the Pareto frontier approximation. Experiments on various multi-objective robot control tasks show that the proposed method clearly outperforms the current state-of-the-art algorithm in terms of both quality and stability of the outcomes.

PA2D-MORL: Pareto Ascent Directional Decomposition Based Multi-Objective Reinforcement Learning | VIDEO

In this paper, we study the collaborative learning model, which concerns the tradeoff between parallelism and communication overhead in multi-agent multi-armed bandits.  For regret minimization in multi-armed bandits, we present the first set of tradeoffs between the number of rounds of communication between the agents and the regret of the collaborative learning process.

Communication-Efficient Collaborative Regret Minimization in Multi-Armed Bandits | VIDEO

Recent advances in event-based research prioritize sparsity and temporal precision. Approaches learning sparse point-based representations through graph CNNs (GCN) become more popular. Yet, these graph techniques hold lower performance than their frame-based counterpart due to two issues: (i) Biased graph structures that don't properly incorporate varied attributes (such as semantics, and spatial and temporal signals) for each vertex, resulting in inaccurate graph representations. (ii) A shortage of robust pretrained models. Here we solve the first problem by proposing a new event-based GCN (EDGCN), with a dynamic aggregation module to integrate all attributes of vertices adaptively. To address the second problem, we introduce a novel learning framework called cross-representation distillation (CRD), which leverages the dense representation of events as a cross-representation auxiliary to provide additional supervision and prior knowledge for the event graph. This frame-to-graph distillation allows us to benefit from the large-scale priors provided by CNNs while still retaining the advantages of graph-based models. Extensive experiments show our model and learning framework are effective and generalize well across multiple vision tasks.

A Dynamic GCN with Cross-Representation Distillation for Event-Based Learning | VIDEO

Online advertising has been one of the most important sources for industry's growth, where the demand-side platforms (DSP) play an important role via bidding to the ad exchanges on behalf of their advertiser clients. Since more and more ad exchanges have shifted from second to first price auctions, it is challenging for DSPs to adjust bidding strategy in the volatile environment. Recent studies on bid shading in first-price auctions may have limited performance due to relatively strong hypotheses about winning probability distribution. Moreover, these studies do not consider the incentive of advertiser clients, which can be crucial for a reliable advertising platform. In this work, we consider both the optimization of bid shading technique and the design of internal auction which is ex-post incentive compatible (IC) for the management of a DSP. Firstly, we prove that the joint design of bid shading and ex-post IC auction can be reduced to choosing one monotone bid function for each advertiser without loss of optimality. Then we propose a parameterized neural network to implement the monotone bid functions. With well-designed surrogate loss, the objective can be optimized in an end-to-end manner. Finally, our experimental results demonstrate the effectiveness and superiority of our algorithm.

Simultaneous Optimization of Bid Shading and Internal Auction for Demand-Side Platforms

Cross-modal hashing~(CMH) is an efficient technique to retrieve relevant data across different modalities, such as images, texts, and videos, which has attracted more and more attention due to its low storage cost and fast query speed. Although existing CMH methods achieve remarkable processes, almost all of them treat all samples of varying difficulty levels without discrimination, thus leaving them vulnerable to noise or outliers. Based on this observation, we reveal and study dual difficulty levels implied in cross-modal hashing learning, \ie instance-level and feature-level difficulty. To address this problem, we propose a novel Dual Self-Paced Cross-Modal Hashing (DSCMH) that mimics human cognitive learning to learn hashing from ``easy'' to ``hard'' in both instance and feature levels, thereby embracing robustness against noise/outliers. Specifically, our DSCMH assigns weights to each instance and feature to measure their difficulty or reliability, and then uses these weights to automatically filter out the noisy and irrelevant data points in the original space. By gradually increasing the weights during training, our method can focus on more instances and features from ``easy'' to ``hard'' in training, thus mitigating the adverse effects of noise or outliers. Extensive experiments are conducted on three widely-used benchmark datasets to demonstrate the effectiveness and robustness of the proposed DSCMH over 12 state-of-the-art CMH methods.

Dual Self-Paced Cross-Modal Hashing

Tactile signals collected by wearable electronics are essential in modeling and understanding human behavior. One of the main applications of tactile signals is action classification, especially in healthcare and robotics. However, existing tactile classification methods fail to capture the spatial and temporal features of tactile signals simultaneously, which results in sub-optimal performances. In this paper, we design Spatio-Temporal Aware tactility Transformer (STAT) to utilize continuous tactile signals for action classification. We propose spatial and temporal embeddings along with a new temporal pretraining task in our model, which aims to enhance the transformer in modeling the spatio-temporal features of tactile signals. Specially, the designed temporal pretraining task is to differentiate the time order of tubelet inputs to model the temporal properties explicitly. Experimental results on a public action classification dataset demonstrate that our model outperforms state-of-the-art methods in all metrics.

Jointly Modeling Spatio-Temporal Features of Tactile Signals for Action Classification

In recent years, object detection in deep learning has experienced rapid development. However, most existing object detection models perform well only on closed-set datasets, ignoring a large number of potential objects whose categories are not defined in the training set. These objects are often identified as background or incorrectly classified as pre-defined categories by the detectors. In this paper, we focus on the challenging problem of Novel Class Discovery and Localization (NCDL), aiming to train detectors that can detect the categories present in the training data, while also actively discover, localize, and cluster new categories. We analyze existing NCDL methods and identify the core issue: object detectors tend to be biased towards seen objects, and this leads to the neglect of unseen targets. To address this issue, we first propose an Debiased Region Mining (DRM) approach that combines class-agnostic Region Proposal Network (RPN) and class-aware RPN in a complementary manner. Additionally, we suggest to improve the representation network through semi-supervised contrastive learning by leveraging unlabeled data. Finally, we adopt a simple and efficient mini-batch K-means clustering method for novel class discovery. We conduct extensive experiments on the NCDL benchmark, and the results demonstrate that the proposed DRM approach significantly outperforms previous methods, establishing a new state-of-the-art.

Downloads

Next from AAAI 2024

Plug-In Diffusion Model for Sequential Recommendation

Similar lecture

Material Removal in Laser Chemical Processing With Modulated Laser Power

.css-70qvj9{display:-webkit-box;display:-webkit-flex;display:-ms-flexbox;display:flex;-webkit-align-items:center;-webkit-box-align:center;-ms-flex-align:center;align-items:center;}Downloads

Next from AAAI 2024

Plug-In Diffusion Model for Sequential Recommendation

Similar lecture

Material Removal in Laser Chemical Processing With Modulated Laser Power

Downloads