Large-Scale Video Search with Efficient Temporal Voting Structure
This work addresses the challenge of efficient video search for users handling large databases with limited computational resources, though it is incremental as it builds on existing hashing and voting methods.
The authors tackled the problem of large-scale video search by developing a fast content-based querying system that uses repeated content representation with edge energy features and efficient hashing, combined with a novel queue-based voting scheme for memory efficiency. The result is a system that achieves fast query times, high recall rates, and very low memory and disk requirements on commodity computers.
In this work, we propose a fast content-based video querying system for large-scale video search. The proposed system is distinguished from similar works with two major contributions. First contribution is superiority of joint usage of repeated content representation and efficient hashing mechanisms. Repeated content representation is utilized with a simple yet robust feature, which is based on edge energy of frames. Each of the representation is converted into hash code with Hamming Embedding method for further queries. Second contribution is novel queue-based voting scheme that leads to modest memory requirements with gradual memory allocation capability, contrary to complete brute-force temporal voting schemes. This aspect enables us to make queries on large video databases conveniently, even on commodity computers with limited memory capacity. Our results show that the system can respond to video queries on a large video database with fast query times, high recall rate and very low memory and disk requirements.