A Unified Metric Learning-Based Framework for Co-Saliency Detection

Han, Junwei; Cheng, Gong; Li, Zhenpeng; Zhang, Dingwen

doi:10.1109/tcsvt.2017.2706264

Cited by 187 publications

(68 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Experimental results demonstrate that the proposed method significantly outperforms some state-of-the-art baselines for those videos being captured under different conditions, including different frame rates, wide baselines, multiple moving objects, planar or non-planar trajectories. In the future work, we will apply the presented approach in this paper to the automated multi-camera surveillance and the co-saliency detection [39][40][41].…”

Section: Resultsmentioning

confidence: 99%

Video Synchronization Based on Projective-Invariant Descriptor

Zhang

Yang

et al. 2018

Neural Process Lett

View full text Add to dashboard Cite

In this paper, we present a novel trajectory-based method to synchronize two videos shooting the same dynamic scene, which are recorded by stationary un-calibrated cameras from different viewpoints. The core algorithm is carried out in two steps: projective-invariant descriptor construction and trajectory points matching. In the first step, a new five-coplanar-points structure is proposed to compute the cross ratio during the construction of the projective-invariant descriptor. The five points include one trajectory point and four fixed points induced from the background scene, which are co-planar in the 3D coordinate. In the second step, the matched trajectory points are initially estimated by the primitive nearest neighbor method, and are further refined by using epipolar geometric constraints and post processing. Experimental results demonstrate that the proposed method significantly outperforms the existing state-of-the-arts. More importantly, the proposed method is more generic in the sense that it works well for those videos captured under different conditions, including different frame rates, wide baseline, multiple moving objects, planar or non-planar motion trajectories.

show abstract

Section: Resultsmentioning

confidence: 99%

Video Synchronization Based on Projective-Invariant Descriptor

Zhang

Yang

et al. 2018

Neural Process Lett

View full text Add to dashboard Cite

show abstract

“…We will also extend the ORSSD dataset and periodically update the results for noticeable salient object detection methods on it. Moreover, some extension works of saliency detection, such as co-saliency detection [52]- [55], will be further extended to optical RSIs in the future.…”

Section: Discussionmentioning

confidence: 99%

Nested Network With Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images

Cong

Hou

et al. 2019

IEEE Trans. Geosci. Remote Sensing

202

123

View full text Add to dashboard Cite

Arising from the various object types and scales, diverse imaging orientations, and cluttered backgrounds in optical remote sensing image (RSI), it is difficult to directly extend the success of salient object detection for nature scene image to the optical RSI. In this paper, we propose an end-to-end deep network called LV-Net based on the shape of network architecture, which detects salient objects from optical RSIs in a purely data-driven fashion. The proposed LV-Net consists of two key modules, i.e., a two-stream pyramid module (L-shaped module) and an encoder-decoder module with nested connections (V-shaped module). Specifically, the L-shaped module extracts a set of complementary information hierarchically by using a twostream pyramid structure, which is beneficial to perceiving the diverse scales and local details of salient objects. The V-shaped module gradually integrates encoder detail features with decoder semantic features through nested connections, which aims at suppressing the cluttered backgrounds and highlighting the salient objects. In addition, we construct the first publicly available optical RSI dataset for salient object detection, including 800 images with varying spatial resolutions, diverse saliency types, and pixel-wise ground truth. Experiments on this benchmark dataset demonstrate that the proposed method outperforms the state-of-the-art salient object detection methods both qualitatively and quantitatively.

show abstract

“…On the whole, co-saliency detection methods are roughly grouped into two categories according to whether the depth cue is introduced, i.e., RGB co-saliency detection [72]- [88] and RGBD co-saliency detection [89]- [92]. Then, the RGB co-saliency detection methods are further divided into some sub-classes based on different correspondence capturing strategies, i.e., matching based method [72]- [79], clustering based method [80], rank analysis based method [81], [82], propagation based method [83], [84], and learning based method [85]- [88]. Different from image data, video sequences contain more abundant appearance information and continuous motion cue, which can better represent the characteristics of the target in a dynamic way.…”

Section: #20mentioning

confidence: 99%

“…Metric learning works on learning a distance metric to make the same-class samples closer and different-class samples as far as possible. Han et al [88] introduced metric learning into co-saliency detection, which jointly learns discriminative feature representation and co-salient object detector via a new objective function. This method has the capacity to handle the wide variation in image scene and achieves superior performance.…”

Section: A Rgb Co-saliency Detectionmentioning

confidence: 99%

Review of Visual Saliency Detection With Comprehensive Information

Cong

Lei

et al. 2019

IEEE Trans. Circuits Syst. Video Technol.

339

130

View full text Add to dashboard Cite

Visual saliency detection model simulates the human visual system to perceive the scene, and has been widely used in many vision tasks. With the development of acquisition technology, more comprehensive information, such as depth cue, inter-image correspondence, or temporal relationship, is available to extend image saliency detection to RGBD saliency detection, co-saliency detection, or video saliency detection. RGBD saliency detection model focuses on extracting the salient regions from RGBD images by combining the depth information. Co-saliency detection model introduces the inter-image correspondence constraint to discover the common salient object in an image group. The goal of video saliency detection model is to locate the motion-related salient object in video sequences, which considers the motion cue and spatiotemporal constraint jointly. In this paper, we review different types of saliency detection algorithms, summarize the important issues of the existing methods, and discuss the existent problems and future works. Moreover, the evaluation datasets and quantitative measurements are briefly introduced, and the experimental analysis and discission are conducted to provide a holistic overview of different saliency detection methods.

show abstract

A Unified Metric Learning-Based Framework for Co-Saliency Detection

Cited by 187 publications

References 52 publications

Video Synchronization Based on Projective-Invariant Descriptor

Video Synchronization Based on Projective-Invariant Descriptor

Nested Network With Two-Stream Pyramid for Salient Object Detection in Optical Remote Sensing Images

Review of Visual Saliency Detection With Comprehensive Information

Contact Info

Product

Resources

About