Adversarial Cross-Modal Retrieval

By Bokun Wang, Yang Yang, Xing Xu, Alan Hanjalic, Heng Tao Shen. ACM Multimedia, 2017

756 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/61060bea27a3410260988540b627ccc5ba131822

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

Citations in the corpus

Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-Modal Pretraining (2021, background): “Cross-modal retrieval [43, 12, 48, 4, 44, 8] emerges as a promising avenue for efficient indexing and searching among large-scale data with different modalities, and is widely used in search engines [2, 14], E-commerce [18, 7], to name a few.”
Deep Multimodal Representation Learning: A Survey (2019, methodology): “Awidely used strategy is classifying the category of learned features such that they are also discriminative within eachmodality [30], [79].”
Heterogeneous Attention Network for Effective and Efficient Cross-modal Retrieval (2021, methodology): “Recently, ACMR [41] exploited adversarial learning to bridge the distribution gap between text features and image features.”
HiT: Hierarchical Transformer with Momentum Contrast for Video-Text Retrieval (2021, background): “Video-Text Retrieval has received wide attention with the exploitation of the huge multimedia data and rich application scenarios.”
Learning Cross-Modal Common Representations by Private–Shared Subspaces Separation (2020, methodology): “Following this idea, during the last decade, a large number of methods [7]– [12] have been proposed to learn common representations for the data of different modalities, which has become the mainstream solution for cross-modal retrieval.”
Scalable Deep Multimodal Learning for Cross-Modal Retrieval (2019, methodology): “…[41] 0.343 0.376 0.330 MvDA-VC [12] 0.397 0.345 0.387 GSS-SL [43] 0.466 0.413 0.440 DCCA [2] 0.301 0.286 0.294 DCCAE [40] 0.308 0.290 0.299 ACMR [38] 0.479 0.426 0.452 CMPM+CMPC [44] 0.493 0.438 0.466 CCL [27] 0.504 0.457 0.481 CBT [30] 0.516 0.464 0.490 SDML 0.522 0.488 0.505 Table 4:…”
Deep Supervised Cross-Modal Retrieval (2019, methodology): “To verify the effectiveness of our proposed methods, we compare the proposed method with ten state-of-the-art methods in the experiments, including five traditional methods, namely CCA [8], MCCA [27], MvDA [10], MvDAVC [11] and JRL [40], as well as five deep learning-based methods, namely CMDN [19],”
Binary Generative Adversarial Networks for Image Retrieval (2017, background): “More recently, deep learning has been introduced in the development of hashing algorithms (Xia et al. 2014; Lin et al. 2016; Do, Doan, and Cheung 2016; Gu, Ma, and Yang 2016; Wang et al. 2017a; Gao et al. 2017; Song et al. 2018), leading to a new generation of deep hashing algorithms.”
A Decade Survey of Content Based Image Retrieval Using Deep Learning (2020, methodology): “The adversarial neural network is also employed for cross-modal retrieval such as adversarial cross-modal retrieval (ACMR) [169], self-supervised adversarial hashing (SSAH) [126], attention-aware deep adversarial hashing (ADAH) [170], adversary guided asymmetric hashing (AGAH) [174], etc.”
Cross-Modality Person Re-Identification with Generative Adversarial Training (2018, methodology): “[Wang et al. , 2017] presented an adversarial cross-modal retrieval method to seek an effective common subspace based on adversarial learning.”
Empowering Things With Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Things (2020, background): “Recent studies on crossmedia matching and retrieval try to align both domains semantically by leveraging deep learning, especially adversarial learning [177].”
Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval (2018, methodology): “The underlined results are reported in ACMR.”
Learn, Imagine and Create: Text-to-Image Generation from Prior Knowledge (2019, methodology): “Additionally, since images and text belong to different domains, it is difficult to directly project them into the same feature space [18, 34, 41].”
Text-to-image Synthesis via Symmetrical Distillation Networks (2018, neutral): “As a multimedia technology, cross-modal retrieval [6, 20, 29, 38, 43] has become a highlighted topic of research in the big data era.”
OPT: Omni-Perception Pre-Trainer for Cross-Modal Understanding and Generation (2021, background): “trieval [42, 10], speech recognition enhanced with video [9, 28], visual question answering [1, 49], visual captioning [48, 26], speech to image generation [44, 21], and textto-image generation [33, 46], etc.”
Joint-modal Distribution-based Similarity Hashing for Large-scale Unsupervised Deep Cross-modal Retrieval (2020, background): “Cross-modalsimilarityretrievalhasbeena popularresearch topic[15, 18, 20–22, 30, 31, 34, 34, 38, 39, 43, 46] with the objective to search the semantic similar instances from different modalities, which has already attracted attention in information retrieval [1, 23] and multimedia analysis [25, 26].”