Dual-Stream Knowledge-Preserving Hashing for Unsupervised Video Retrieval
Unsupervised video hashing usually optimizes binary codes by learning to reconstruct input videos. Such reconstruction constraint spends much effort on frame-level temporal context changes without focusing on video-level global semantics that are more useful for retrieval. Hence, we address this problem by decomposing video information into reconstruction-dependent and semantic-dependent information, which disentangles the semantic extraction from reconstruction constraint. Specifically, we first design a simple dual-stream structure, including a temporal layer and a hash layer. Then, with the help of semantic similarity knowledge obtained from self-supervision, the hash layer learns to capture information for semantic retrieval, while the temporal layer learns to capture the information for reconstruction. In this way, the model naturally preserves the disentangled semantics into binary codes. Validated by comprehensive experiments, our method consistently outperforms the state-of-the-arts on three video benchmarks.
Code (0)
등록된 구현이 없습니다.
Tasks
RetrievalSemantic RetrievalSemantic SimilaritySemantic Textual SimilarityVideo RetrievalSimilar Papers 제목 키워드 기반
ViT2Hash: Unsupervised Information-Preserving Hashing
Unsupervised image hashing, which maps images into binary codes without supervision, is a compressor with a high compression rate. Hence, how to preserving meaningful information of the original data is a critical proble…
QuantizationObject Detection based Deep Unsupervised Hashing
Recently, similarity-preserving hashing methods have been extensively studied for large-scale image retrieval. Compared with unsupervised hashing, supervised hashing methods for labeled data have usually better performan…
Image RetrievalNovel Object DetectionObjectobject-detection+2Unsupervised Semantic Deep Hashing
In recent years, deep hashing methods have been proved to be efficient since it employs convolutional neural network to learn features and hashing codes simultaneously. However, these methods are mostly supervised. In re…
Deep HashingImage RetrievalQuantizationRetrievalDeep Residual Hashing
Hashing aims at generating highly compact similarity preserving code words which are well suited for large-scale image retrieval tasks. Most existing hashing methods first encode the images as a vector of hand-crafted …
BinarizationImage RetrievalQuantizationRepresentation Learning+1Deep Unsupervised Hashing by Distilled Smooth Guidance
Hashing has been widely used in approximate nearest neighbor search for its storage and computational efficiency. Deep supervised hashing methods are not widely used because of the lack of labeled data, especially when t…
ClusteringComputational EfficiencyDeep Hashing