DeepAI AI Chat
Log In Sign Up

Fine-Grained Instance-Level Sketch-Based Video Retrieval

by   Peng Xu, et al.
Beijing University of Posts and Telecommunications
University of Surrey
Nanyang Technological University

Existing sketch-analysis work studies sketches depicting static objects or scenes. In this work, we propose a novel cross-modal retrieval problem of fine-grained instance-level sketch-based video retrieval (FG-SBVR), where a sketch sequence is used as a query to retrieve a specific target video instance. Compared with sketch-based still image retrieval, and coarse-grained category-level video retrieval, this is more challenging as both visual appearance and motion need to be simultaneously matched at a fine-grained level. We contribute the first FG-SBVR dataset with rich annotations. We then introduce a novel multi-stream multi-modality deep network to perform FG-SBVR under both strong and weakly supervised settings. The key component of the network is a relation module, designed to prevent model over-fitting given scarce training data. We show that this model significantly outperforms a number of existing state-of-the-art models designed for video analysis.


page 1

page 4

page 10

page 11


Sketch Less for More: On-the-Fly Fine-Grained Sketch Based Image Retrieval

Fine-grained sketch-based image retrieval (FG-SBIR) addresses the proble...

Universal Perceptual Grouping

In this work we aim to develop a universal sketch grouper. That is, a gr...

Generic Sketch-Based Retrieval Learned without Drawing a Single Sketch

We cast the sketch-based retrieval as edge-map matching. A shared convol...

Product1M: Towards Weakly Supervised Instance-Level Product Retrieval via Cross-modal Pretraining

Nowadays, customer's demands for E-commerce are more diversified, which ...

Towards Fine-Grained Billing For Cloud Networking

We revisit multi-tenant network virtualization in data centers, and make...

Deep Reinforced Attention Regression for Partial Sketch Based Image Retrieval

Fine-Grained Sketch-Based Image Retrieval (FG-SBIR) aims at finding a sp...

Generalisation and Sharing in Triplet Convnets for Sketch based Visual Search

We propose and evaluate several triplet CNN architectures for measuring ...