Deep Learning for Content-Based Image Retrieval: A Comprehensive Study

By Ji Wan, Dayong Wang, Steven C. H. Hoi, Pengcheng Wu, Jianke Zhu, Yongdong Zhang, Jintao Li. ACM Multimedia, 2014

938 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/391b86cf16c2702dcc4beee55a6dd6d3bd7cf27b

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Media Technology

Citations in the corpus

Multi-Scale Dense Networks for Resource Efficient Image Classification (2017, background): “Recent years have witnessed a surge in demand for applications of visual object recognition, for instance, in self-driving cars (Bojarski et al., 2016) and content-based image search (Wan et al., 2014).”
Multi-task deep visual-semantic embedding for video thumbnail selection (2015, methodology): “Before training, we init the CNN with the parameters trained well in [21].”
A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, background): “A huge progress has been made in this decade to utilize the power of deep learning for content based image retrieval [46], [47], [48], [49].”
Coarse-to-Fine Description for Fine-Grained Visual Categorization (2016, methodology): “As the Convolutional Neural Network has achieved amazing performance in various task for computer vision [11], [26], [43]–[45], we then employ the Convolutional Neural Networks as the feature extractor.”
Exploiting local features from deep networks for image retrieval (2015, background): “[32] conducted a comprehensive study on applying CNN features to real-world image retrieval with model retraining and similarity learning.”
Deep learning in agriculture: A survey (2018, background): “To the authors’ knowledge, this is the first such survey in the agricultural domain, while a small number of more general surveys do exist (Deng and Yu, 2014; Wan et al., 2014; Najafabadi et al., 2015), covering related work in DL in other domains.”
A Hybrid Deep Learning Architecture for Privacy-Preserving Mobile Analytics (2017, methodology): “of the most widely used DNN architectures [8]–[10] to build accurate models for gender and activity recognition.”
Collaborative Metric Learning (2017, neutral): “[43, 45, 26, 52, 32].”
Object Detection With Deep Learning: A Review (2018, methodology): “Due to these advantages, CNN has been widely applied into many research fields, such as image super-resolution reconstruction [54], [55], image classification [5], [56], image retrieval [57], [58], face recognition [8][S5], pedestrian detection [59]–[61] and video analysis [62], [63].”
Glance and Focus: a Dynamic Approach to Reducing Spatial Redundancy in Image Classification (2020, background): “In real-world applications like content-based image search [54] or autonomous vehicles [3], computation usually translates into latency and power consumption, which should be minimized for both safety and economical reasons [17, 21, 43].”
DeepStore: In-Storage Acceleration for Intelligent Queries (2019, methodology): “In the case of intelligent-query systems, such indices cannot be built due to the non-linearity introduced by extracting feature vectors from DNN models and query diversity [16, 22, 90, 106].”
Weakly Supervised Scene Parsing with Point-based Distance Metric Learning (2018, methodology): “2009), image retrieval (Wan et al. 2014) and editing (Tsai et al.”
A Review on Deep Learning Techniques Applied to Semantic Segmentation (2017, background): “Some of those applications include autonomous driving [1] [2] [3], human-machine interaction [4], computational photography [5], image search engines [6], and augmented reality to name a few.”
Learning Compact Binary Descriptors with Unsupervised Deep Neural Networks (2016, methodology): “Given compact binary descriptors, one can rapidly measure the similarity of the images by computing the Hamming distance between binary descriptors via XOR bitwise operations.”
Correlation Hashing Network for Efficient Cross-Modal Retrieval (2016, background): “Other cross-modal retrieval models via deep learning [Masci et al., 2014; Srivastava and Salakhutdinov, 2014; Wang et al., 2014b; Wan et al., 2014; Jiang and Li, 2016] have shown that deep models can capture nonlinear cross-modal correlations more effectively and yielded state-of-the-art results on…”
Deep learning for visual understanding: A review (2016, methodology): “Given the recent successes that deep learning techniques have achieved, the research presented in [166] attempts to evaluate if deep learning can bridge the semantic gap in content-based image retrieval (CBIR).”