Search Results for author: Shitong Sun

Found 5 papers, 0 papers with code

Training-free Zero-shot Composed Image Retrieval with Local Concept Reranking

no code implementations14 Dec 2023 Shitong Sun, Fanghua Ye, Shaogang Gong

Composed image retrieval attempts to retrieve an image of interest from gallery images through a composed query of a reference image and its corresponding modified text.

Image Retrieval Re-Ranking +2

Benchmarking Robustness of Text-Image Composed Retrieval

no code implementations24 Nov 2023 Shitong Sun, Jindong Gu, Shaogang Gong

In this paper, we perform the first robustness study and establish three new diversified benchmarks for systematic analysis of text-image composed retrieval against natural corruptions in both vision and text and further probe textural understanding.

Attribute Benchmarking +1

FSAR: Federated Skeleton-based Action Recognition with Adaptive Topology Structure and Knowledge Distillation

no code implementations ICCV 2023 Jingwen Guo, Hong Liu, Shitong Sun, Tianyu Guo, Min Zhang, Chenyang Si

Existing skeleton-based action recognition methods typically follow a centralized learning paradigm, which can pose privacy concerns when exposing human-related videos.

Action Recognition Federated Learning +3

Exploring Semantic Attributes from A Foundation Model for Federated Learning of Disjoint Label Spaces

no code implementations29 Aug 2022 Shitong Sun, Chenyang Si, Guile Wu, Shaogang Gong

To resolve this problem, federated learning has been introduced to transfer knowledge across multiple sources (clients) with non-shared data while optimising a globally generalised central model (server).

Attribute Federated Learning +3

Decentralised Person Re-Identification with Selective Knowledge Aggregation

no code implementations21 Oct 2021 Shitong Sun, Guile Wu, Shaogang Gong

This helps to preserve model personalisation knowledge on each local client domain and learn instance-specific information.

Person Re-Identification

Cannot find the paper you are looking for? You can Submit a new open access paper.