Dynamic visual attention: searching for coding length increments

By Xiaodi Hou, Liqing Zhang. Neural Information Processing Systems, 2008

488 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/4e7ec75337766f2b649bb9f99c6887ee0f1674a6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Wenguan Wang
2. Ali Borji
3. Jianbing Shen
4. Ming-Ming Cheng
5. Junwei Han
6. Deng-Ping Fan
7. Huchuan Lu
8. Gong Cheng

Citations in the corpus

• Depth Matters: Influence of Depth Cues on Visual Saliency (2012, methodology): “0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 FALSE POSITIVE RATE TRUE POSITIVE RATE IT GBVS FT ICL AIM LSK LRR 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.”
• State-of-the-Art in Visual Attention Modeling (2013, background): “Zhang et al. [141] proposed a definition of saliency known as SUN, Saliency Using Natural statistics, by considering what the visual system is trying to optimize when directing attention.”
• Background Prior-Based Salient Object Detection via Deep Reconstruction Residual (2015, background): “A few recent approaches tried to learn better representations from natural scenes for saliency detection using independent component analysis [8], sparse coding [9], [10], and low-rank matrix recovery [11].”
• The Secrets of Salient Object Segmentation (2014, methodology): “In this section, we benchmark 7 fixations algorithms, AWS [13], AIM [6], SIG [15], DVA [16], GBVS [14], SUN [26], and ITTI [17] on 5 datasets, Bruce [6], Cerf [8], IS [20], Judd [18], and our PASCAL-S.”
• Revisiting Video Saliency: A Large-Scale Benchmark and a New Model (2018, background): “[14, 16, 41, 50, 52, 23, 13, 20, 37] leveraged both static stimulus features and temporal information (e.”
• A Deep Network Solution for Attention and Aesthetics Aware Photo Cropping (2019, methodology): “els [18], [19], [21], [22], [23] typically generate saliency cues”
• Static and space-time visual saliency detection by self-resemblance. (2009, methodology): “…visual saliency detection has been of great research interest (Bruce & Tsotsos, 2006; Gao, Mahadevan, &Vasconcelos, 2008; Gao & Vasconcelos, 2005; Hou & Zhang, 2008a; Hou & Zhang, 2008b; Itti, Koch, & Niebur, 1998; Kanan, Tong, Zhang, & Cottrell, 2009; Marat et al., 2009; Torralba, Fergus, &…”
• Two-Stage Learning to Predict Human Eye Fixations via SDAEs (2016, methodology): “However, as pointed out by Zhang et al. [36], strong center-bias may exist in human fixations and it can influence the performance of a saliency model.”
• Exploiting local and global patch rarities for saliency detection (2012, background): “Among compared models, ICL [12], AIM [14], SDSR [11], and Judd et al. [3] performed higher than the rest.”
• Revisiting Video Saliency Prediction in the Deep Learning Era (2021, methodology): “For the non-deep learning methods, ITTI [26] is the fastest method (0.9s per frame on CPU) among static models and Hou et al. [13] is the fastest dynamic saliency model (0.7s per frame on CPU).”
• Quantitative Analysis of Human-Model Agreement in Visual Saliency Modeling: A Comparative Study (2013, background): “[43] 2008 I M W × H 22 Kootstra: Kootstra and Shomacker [44] 2008 I E W × H”
• Visual saliency detection by spatially weighted dissimilarity (2011, methodology): “Hou et al. [18] introduced the Incremental Coding Length (ICL) to measure the perspective entropy gain from each feature.”
• Contextual Hypergraph Modeling for Salient Object Detection (2013, methodology): “Various contrast measures have been proposed, including mutual information [22], incremental coding length [3], and centerImage SVM saliency Hypergraph saliency”
• Large-Scale Optimization of Hierarchical Features for Saliency Prediction in Natural Images (2014, methodology): “To ro nt o Chance – 0.4988 – 4.1171 – 0.3040 – -0.0038 Cntr 0.7836 – 2.5828 – 0.4116 – 0.8180 – CovSal 0.8147 0.7616 2.3712 3.1187 0.5122 0.3812 1.4587 1.0090 ICL 0.8169 0.7807 2.4190 2.9943 0.5253 0.4333 1.6199 1.2483 Signature 0.8188 0.7903 2.3776 2.9054 0.5311 0.4658 1.5888 1.4464 GBVS 0.8274 0.8”
• Saliency and Human Fixations: State-of-the-Art and Study of Comparison Metrics (2013, background): “AIM [6], DVA [10] and RARE [25] are into the information theoretic category.”
• Learning Unsupervised Video Object Segmentation Through Visual Attention (2019, methodology): “Early attention models [42, 90, 19, 6, 22, 25, 36, 15, 20, 26, 61, 22] are based on biologically-inspired features (color, edge, optical flow, etc .) and cognitive theories about visual attention (attention shift [39], feature integration theory [68], guided search [82], etc .).”