Set-to-set Hashing With Applications In Visual Recognition

Abstract

Visual data, such as an image or a sequence of video frames, is often naturally represented as a point set. In this paper, we consider the fundamental problem of finding a nearest set from a collection of sets, to a query set. This problem has obvious applications in large-scale visual retrieval and recognition, and also in applied fields beyond computer vision. One challenge stands out in solving the problem---set representation and measure of similarity. Particularly, the query set and the sets in dataset collection can have varying cardinalities. The training collection is large enough such that linear scan is impractical. We propose a simple representation scheme that encodes both statistical and structural information of the sets. The derived representations are integrated in a kernel framework for flexible similarity measurement. For the query set process, we adopt a learning-to-hash pipeline that turns the kernel representations into hash bits based on simple learners, using mul

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyjhuo2017set

Related papers

• SLOSH: Set Locality Sensitive Hashing Via Sliced-wasserstein Embeddings (2021)5.24
• Deep Image Set Hashing (2016)7.81
• A Survey On Learning To Hash (2016)21.62
• Query-adaptive Hash Code Ranking For Large-scale Multi-view Visual Search (2019)13.74
• Deep Hashing: A Joint Approach For Image Signature Learning (2016)5.24
• Unsupervised Deep Hashing For Large-scale Visual Search (2016)9.59
• Deep Heterogeneous Hashing For Face Video Retrieval (2019)9.92
• Robust Hashing For Multi-view Data: Jointly Learning Low-rank Kernelized Similarity Consensus And Hash Functions (2016)11.19