| 1. |
- Chatterjee, Bapi, 1982
(författare)
-
Lock-free Concurrent Search
- 2017
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The contemporary computers typically consist of multiple computing cores with high compute power. Such computers make excellent concurrent asynchronous shared memory system. On the other hand, though many celebrated books on data structure and algorithm provide a comprehensive study of sequential search data structures, unfortunately, we do not have such a luxury if concurrency comes in the setting. The present dissertation aims to address this paucity. We describe novel lock-free algorithms for concurrent data structures that target a variety of search problems.(i) Point search (membership query, predecessor query, nearest neighbour query) for 1-dimensional data: Lock-free linked-list; lock-free internal and external binary search trees (BST).(ii) Range search for 1-dimensional data: A range search method for lock-free ordered set data structures - linked-list, skip-list and BST.(iii) Point search for multi-dimensional data: Lock-free kD-tree, specially, a generic method for nearest neighbour search.We prove that the presented algorithms are linearizable i.e. the concurrent data structure operations intuitively display their sequential behaviour to an observer of the concurrent system. The lock-freedom in the introduced algorithms guarantee overall progress in an asynchronous shared memory system. We present the amortized analysis of lock-free data structures to show their efficiency. Moreover, we provide sample implementations of the algorithms and test them over extensive micro-benchmarks. Our experiments demonstrate that the implementations are scalable and perform well when compared to related existing alternative implementations on common multi-core computers.Our focus is on propounding the generic methodologies for efficient lock-free concurrent search. In this direction, we present the notion of help-optimality, which captures the optimization of amortized step complexity of the operations. In addition to that, we explore the language-portable design of lock-free data structures that aims to simplify an implementation from programmer’s point of view. Finally, our techniques to implement lock-free linearizable range search and nearest neighbour search are independent of the underlying data structures and thus are adaptive to similar data structures.
|
|
| 2. |
- Norlund, Tobias, 1991, et al.
(författare)
-
Transferring Knowledge from Vision to Language: How to Achieve it and how to Measure it?
- 2021
-
Ingår i: Proceedings of the Fourth BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP, pp. 149-162, Punta Cana, Dominican Republic. - : Association for Computational Linguistics.
-
Konferensbidrag (refereegranskat)abstract
- Large language models are known to suffer from the hallucination problem in that they are prone to output statements that are false or inconsistent, indicating a lack of knowledge. A proposed solution to this is to provide the model with additional data modalities that complements the knowledge obtained through text. We investigate the use of visual data to complement the knowledge of large language models by proposing a method for evaluating visual knowledge transfer to text for uni- or multimodal language models. The method is based on two steps, 1) a novel task querying for knowledge of memory colors, i.e. typical colors of well-known objects, and 2) filtering of model training data to clearly separate knowledge contributions. Additionally, we introduce a model architecture that involves a visual imagination step and evaluate it with our proposed method. We find that our method can successfully be used to measure visual knowledge transfer capabilities in models and that our novel model architecture shows promising results for leveraging multimodal knowledge in a unimodal setting.
|
|
| 3. |
- Yun, Yixiao, 1987, et al.
(författare)
-
Maximum-Likelihood Object Tracking from Multi-View Video by Combining Homography and Epipolar Constraints
- 2012
-
Ingår i: 6th ACM/IEEE Int'l Conf on Distributed Smart Cameras (ICDSC 12), Oct 30 - Nov.2, 2012, Hong Kong. - 9781450317726 ; , s. 6 pages-
-
Konferensbidrag (refereegranskat)abstract
- This paper addresses problem of object tracking in occlusion scenarios, where multiple uncalibrated cameras with overlapping fields of view are used. We propose a novel method where tracking is first done independently for each view and then tracking results are mapped between each pair of views to improve the tracking in individual views, under the assumptions that objects are not occluded in all views and move uprightly on a planar ground which may induce a homography relation between each pair of views. The tracking results are mapped by jointly exploiting the geometric constraints of homography, epipolar and vertical vanishing point. Main contributions of this paper include: (a) formulate a reference model of multi-view object appearance using region covariance for each view; (b) define a likelihood measure based on geodesics on a Riemannian manifold that is consistent with the destination view by mapping both the estimated positions and appearances of tracked object from other views; (c) locate object in each individual view based on maximum likelihood criterion from multi-view estimations of object position. Experiments have been conducted on videos from multiple uncalibrated cameras, where targets experience long-term partial or full occlusions. Comparison with two existing methods and performance evaluations are also made. Test results have shown effectiveness of the proposed method in terms of robustness against tracking drifts caused by occlusions.
|
|
| 4. |
- Liu, Yuanhua, 1971, et al.
(författare)
-
Considering the importance of user profiles in interface design
- 2009
-
Ingår i: User Interfaces. ; , s. 23-
-
Bokkapitel (övrigt vetenskapligt/konstnärligt)abstract
- User profile is a popular term widely employed during product design processes by industrial companies. Such a profile is normally intended to represent real users of a product. The ultimate purpose of a user profile is actually to help designers to recognize or learn about the real user by presenting them with a description of a real user’s attributes, for instance; the user’s gender, age, educational level, attitude, technical needs and skill level. The aim of this chapter is to provide information on the current knowledge and research about user profile issues, as well as to emphasize the importance of considering these issues in interface design. In this chapter, we mainly focus on how users’ difference in expertise affects their performance or activity in various interaction contexts. Considering the complex interaction situations in practice, novice and expert users’ interactions with medical user interfaces of different technical complexity will be analyzed as examples: one focuses on novice and expert users’ difference when interacting with simple medical interfaces, and the other focuses on differences when interacting with complex medical interfaces. Four issues will be analyzed and discussed: (1) how novice and expert users differ in terms of performance during the interaction; (2) how novice and expert users differ in the perspective of cognitive mental models during the interaction; (3) how novice and expert users should be defined in practice; and (4) what are the main differences between novice and expert users’ implications for interface design. Besides describing the effect of users’ expertise difference during the interface design process, we will also pinpoint some potential problems for the research on interface design, as well as some future challenges that academic researchers and industrial engineers should face in practice.
|
|
| 5. |
- Rumman, Nadine Abu, et al.
(författare)
-
Skin deformation methods for interactive character animation
- 2017
-
Ingår i: Communications in Computer and Information Science. - Cham : Springer International Publishing. - 1865-0937 .- 1865-0929. ; 693, s. 153-174, s. 153-174
-
Konferensbidrag (refereegranskat)abstract
- Character animation is a vital component of contemporary computer games, animated feature films and virtual reality applications. The problem of creating appealing character animation can best be described by the title of the animation bible: “The Illusion of Life”. The focus is not on completing a given motion task, but more importantly on how this motion task is performed by the character. This does not necessarily require realistic behavior, but behavior that is believable. This of course includes the skin deformations when the character is moving. In this paper, we focus on the existing research in the area of skin deformation, ranging from skeleton-based deformation and volume preserving techniques to physically based skinning methods. We also summarize the recent contributions in deformable and soft body simulations for articulated characters, and discuss various geometric and example-based approaches. © Springer International Publishing AG 2017.
|
|
| 6. |
- Fu, Keren, et al.
(författare)
-
Deepside: A general deep framework for salient object detection
- 2019
-
Ingår i: Neurocomputing. - : Elsevier BV. - 0925-2312 .- 1872-8286. ; 356, s. 69-82
-
Tidskriftsartikel (refereegranskat)abstract
- Deep learning-based salient object detection techniques have shown impressive results compared to con- ventional saliency detection by handcrafted features. Integrating hierarchical features of Convolutional Neural Networks (CNN) to achieve fine-grained saliency detection is a current trend, and various deep architectures are proposed by researchers, including “skip-layer” architecture, “top-down” architecture, “short-connection” architecture and so on. While these architectures have achieved progressive improve- ment on detection accuracy, it is still unclear about the underlying distinctions and connections between these schemes. In this paper, we review and draw underlying connections between these architectures, and show that they actually could be unified into a general framework, which simply just has side struc- tures with different depths. Based on the idea of designing deeper side structures for better detection accuracy, we propose a unified framework called Deepside that can be deeply supervised to incorporate hierarchical CNN features. Additionally, to fuse multiple side outputs from the network, we propose a novel fusion technique based on segmentation-based pooling, which severs as a built-in component in the CNN architecture and guarantees more accurate boundary details of detected salient objects. The effectiveness of the proposed Deepside scheme against state-of-the-art models is validated on 8 benchmark datasets.
|
|
| 7. |
- Isaksson, Martin, et al.
(författare)
-
Adaptive Expert Models for Federated Learning
- 2023
-
Ingår i: <em>Lecture Notes in Computer Science </em>Volume 13448 Pages 1 - 16 2023. - Cham : Springer Science and Business Media Deutschland GmbH. - 9783031289958 ; 13448 LNAI, s. 1-16
-
Konferensbidrag (refereegranskat)abstract
- Federated Learning (FL) is a promising framework for distributed learning when data is private and sensitive. However, the state-of-the-art solutions in this framework are not optimal when data is heterogeneous and non-IID. We propose a practical and robust approach to personalization in FL that adjusts to heterogeneous and non-IID data by balancing exploration and exploitation of several global models. To achieve our aim of personalization, we use a Mixture of Experts (MoE) that learns to group clients that are similar to each other, while using the global models more efficiently. We show that our approach achieves an accuracy up to 29.78% better than the state-of-the-art and up to 4.38% better compared to a local model in a pathological non-IID setting, even though we tune our approach in the IID setting. © 2023, The Author(s)
|
|
| 8. |
- Lindén, Joakim, et al.
(författare)
-
Evaluating the Robustness of ML Models to Out-of-Distribution Data Through Similarity Analysis
- 2023
-
Ingår i: Commun. Comput. Info. Sci.. - : Springer Science and Business Media Deutschland GmbH. - 9783031429408 ; , s. 348-359, s. 348-359
-
Konferensbidrag (refereegranskat)abstract
- In Machine Learning systems, several factors impact the performance of a trained model. The most important ones include model architecture, the amount of training time, the dataset size and diversity. We present a method for analyzing datasets from a use-case scenario perspective, detecting and quantifying out-of-distribution (OOD) data on dataset level. Our main contribution is the novel use of similarity metrics for the evaluation of the robustness of a model by introducing relative Fréchet Inception Distance (FID) and relative Kernel Inception Distance (KID) measures. These relative measures are relative to a baseline in-distribution dataset and are used to estimate how the model will perform on OOD data (i.e. estimate the model accuracy drop). We find a correlation between our proposed relative FID/relative KID measure and the drop in Average Precision (AP) accuracy on unseen data.
|
|
| 9. |
- Frid, Emma, et al.
(författare)
-
Perception of Mechanical Sounds Inherent to Expressive Gestures of a NAO Robot - Implications for Movement Sonification of Humanoids
- 2018
-
Ingår i: Proceedings of the 15th Sound and Music Computing Conference. - Limassol, Cyprus. - 9789963697304
-
Konferensbidrag (refereegranskat)abstract
- In this paper we present a pilot study carried out within the project SONAO. The SONAO project aims to compen- sate for limitations in robot communicative channels with an increased clarity of Non-Verbal Communication (NVC) through expressive gestures and non-verbal sounds. More specifically, the purpose of the project is to use move- ment sonification of expressive robot gestures to improve Human-Robot Interaction (HRI). The pilot study described in this paper focuses on mechanical robot sounds, i.e. sounds that have not been specifically designed for HRI but are inherent to robot movement. Results indicated a low correspondence between perceptual ratings of mechanical robot sounds and emotions communicated through ges- tures. In general, the mechanical sounds themselves ap- peared not to carry much emotional information compared to video stimuli of expressive gestures. However, some mechanical sounds did communicate certain emotions, e.g. frustration. In general, the sounds appeared to commu- nicate arousal more effectively than valence. We discuss potential issues and possibilities for the sonification of ex- pressive robot gestures and the role of mechanical sounds in such a context. Emphasis is put on the need to mask or alter sounds inherent to robot movement, using for exam- ple blended sonification.
|
|
| 10. |
- Frid, Emma, 1988-, et al.
(författare)
-
Perceptual Evaluation of Blended Sonification of Mechanical Robot Sounds Produced by Emotionally Expressive Gestures : Augmenting Consequential Sounds to Improve Non-verbal Robot Communication
- 2021
-
Ingår i: International Journal of Social Robotics. - : Springer Nature. - 1875-4791 .- 1875-4805.
-
Tidskriftsartikel (refereegranskat)abstract
- This paper presents two experiments focusing on perception of mechanical sounds produced by expressive robot movement and blended sonifications thereof. In the first experiment, 31 participants evaluated emotions conveyed by robot sounds through free-form text descriptions. The sounds were inherently produced by the movements of a NAO robot and were not specifically designed for communicative purposes. Results suggested no strong coupling between the emotional expression of gestures and how sounds inherent to these movements were perceived by listeners; joyful gestures did not necessarily result in joyful sounds. A word that reoccurred in text descriptions of all sounds, regardless of the nature of the expressive gesture, was “stress”. In the second experiment, blended sonification was used to enhance and further clarify the emotional expression of the robot sounds evaluated in the first experiment. Analysis of quantitative ratings of 30 participants revealed that the blended sonification successfully contributed to enhancement of the emotional message for sound models designed to convey frustration and joy. Our findings suggest that blended sonification guided by perceptual research on emotion in speech and music can successfully improve communication of emotions through robot sounds in auditory-only conditions.
|
|
