Multimodal weighted dictionary learning

Taalimi, Ali; Shams, Hesam; Rahimpour, Alireza; Khorsandi, Rahman; Wang, Wei; Guo, Rui

doi:10.1109/avss.2016.7738026

Cited by 4 publications

(5 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…F is the Frobenius norm. When λ 2 > 0 problem (2) is a generalization of elastic-net optimization [21] and it has been proved in [25,17] that it leads to more stable results. Fusion in physical space would be grouping in space of sparse codes and is enforced by A i 12 = p r=1 A r→ 2 ; where A r→ is the r-th row in A i .…”

Section: Multi-view Task Driven Dictionary Learningmentioning

confidence: 99%

“…Hence, the bi-level optimization is solved by splitting to two sub-problems, and in each sub-problem, we solve the optimization for one variable while others are fixed. We solve the proposed bi-level optimization problem ( 2) and ( 3) following [17,26] using the SPArse Modeling Software [27].…”

Section: Multi-view Task Driven Dictionary Learningmentioning

confidence: 99%

“…One solution is information fusion from different sensors that has been demonstrated to be more robust to sensor failure [16]. For instance, each camera is considered as a modality in [17] and feature-fusion techniques is applied which led to a superior multi-view action recognition.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Multi-view task-driven recognition in visual sensor networks

Taalimi

Rahimpour

Liu

et al. 2017

2017 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

Nowadays, distributed smart cameras are deployed for a wide set of tasks in several application scenarios, ranging from object recognition, image retrieval, and forensic applications. Due to limited bandwidth in distributed systems, efficient coding of local visual features has in fact been an active topic of research. In this paper, we propose a novel approach to obtain a compact representation of high-dimensional visual data using sensor fusion techniques. We convert the problem of visual analysis in resource-limited scenarios to a multiview representation learning, and we show that the key to finding properly compressed representation is to exploit the position of cameras with respect to each other as a normbased regularization in the particular signal representation of sparse coding. Learning the representation of each camera is viewed as an individual task and a multi-task learning with joint sparsity for all nodes is employed. The proposed representation learning scheme is referred to as the multi-view task-driven learning for visual sensor network (MT-VSN). We demonstrate that MT-VSN outperforms state-of-the-art in various surveillance recognition tasks.

show abstract

Section: Multi-view Task Driven Dictionary Learningmentioning

confidence: 99%

Section: Multi-view Task Driven Dictionary Learningmentioning

confidence: 99%

See 1 more Smart Citation

Multi-view task-driven recognition in visual sensor networks

Taalimi

Rahimpour

Liu

et al. 2017

2017 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

show abstract

“…where P i is n×m i matrix, where each column denotes one of the basis functions from the corresponding subspace/dictionary. We would like to note that here we assume that both subspaces are known, in the applications where the choice of subspaces/dictionaries is not clear, we can use dictionary/subspace learning algorithms to learn them [18]- [23].…”

Section: Problem Formulationmentioning

confidence: 99%

Text extraction from texture images using masked signal decomposition

Minaee

Wang

2017

2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP)

View full text Add to dashboard Cite

Text extraction is an important problem in image processing with applications from optical character recognition to autonomous driving. Most of the traditional text segmentation algorithms consider separating text from a simple background (which usually has a different color from texts). In this work we consider separating texts from a textured background, that has similar color to texts. We look at this problem from a signal decomposition perspective, and consider a more realistic scenario where signal components are overlaid on top of each other (instead of adding together). When the signals are overlaid, to separate signal components, we need to find a binary mask which shows the support of each component. Because directly solving the binary mask is intractable, we relax this problem to the approximated continuous problem, and solve it by alternating optimization method. We show that the proposed algorithm achieves significantly better results than other recent works on several challenging images.

show abstract

“…They fail when objects overlap each other objects or by fixed objects in the scene like trees and poles which leads to miss-detections, false positives, and incorrect responses. Several recent algorithms address this issue in a combinatorial optimization framework [1,8,9].…”

Section: Introductionmentioning

confidence: 99%

Addressing ambiguity in multi-target tracking by hierarchical strategy

Taalimi

Liu

2017

2017 IEEE International Conference on Image Processing (ICIP)

Self Cite

View full text Add to dashboard Cite

This paper presents a novel hierarchical approach for the simultaneous tracking of multiple targets in a video. We use a network flow approach to link detections in low-level and tracklets in high-level. At each step of the hierarchy, the confidence of candidates is measured by using a new scoring system, ConfRank, that considers the quality and the quantity of its neighborhood. The output of the first stage is a collection of safe tracklets and unlinked high-confidence detections. For each individual detection, we determine if it belongs to an existing or is a new tracklet. We show the effect of our framework to recover missed detections and reduce switch identity. The proposed tracker is referred to as TVOD for multi-target tracking using the visual tracker and generic object detector. We achieve competitive results with lower identity switches on several datasets comparing to state-of-the-art.

show abstract

Multimodal weighted dictionary learning

Cited by 4 publications

References 26 publications

Multi-view task-driven recognition in visual sensor networks

Multi-view task-driven recognition in visual sensor networks

Text extraction from texture images using masked signal decomposition

Addressing ambiguity in multi-target tracking by hierarchical strategy

Contact Info

Product

Resources

About