Search Results for author:
Found 15 papers, 11 papers with code
PTVD: A Large-Scale Plot-Oriented Multimodal Dataset Based on Television Dramas
Art forms such as movies and television (TV) dramas are reflections of the real world, which have attracted much attention from the multimodal learning community recently.
Knowledge-augmented Few-shot Visual Relation Detection
Inspired by this, we devise a knowledge-augmented, few-shot VRD framework leveraging both textual knowledge and visual relation knowledge to improve the generalization ability of few-shot VRD.
Binary Embedding-based Retrieval at Tencent
To tackle the challenge, we propose a binary embedding-based retrieval (BEBR) engine equipped with a recurrent binarization algorithm that enables customized bits per dimension.
Darwinian Model Upgrades: Model Evolving with Selective Compatibility
The traditional model upgrading paradigm for retrieval requires recomputing all gallery embeddings before deploying the new model (dubbed as "backfilling"), which is quite expensive and time-consuming considering billions of instances in industrial applications.
Generative Model Watermarking Based on Human Visual System
Intellectual property protection of deep neural networks is receiving attention from more and more researchers, and the latest research applies model watermarking to generative models for image processing.
Privacy-Preserving Model Upgrades with Bidirectional Compatible Training in Image Retrieval
The task of privacy-preserving model upgrades in image retrieval desires to reap the benefits of rapidly evolving new models without accessing the raw gallery images.
Aesthetic Text Logo Synthesis via Content-aware Layout Inferring
To train and evaluate our approach, we construct a dataset named as TextLogo3K, consisting of about 3, 500 text logo images and their pixel-level annotations.
Towards Universal Backward-Compatible Representation Learning
The task of backward-compatible representation learning is therefore introduced to support backfill-free model upgrades, where the new query features are interoperable with the old gallery features.
Information Gain Propagation: a new way to Graph Active Learning with Soft Labels
Graph Neural Networks (GNNs) have achieved great success in various tasks, but their performance highly relies on a large number of labeled nodes, which typically requires considerable human effort.
Hot-Refresh Model Upgrades with Regression-Alleviating Compatible Training in Image Retrieval
In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly.
Contrastive Spatio-Temporal Pretext Learning for Self-supervised Video Representation
Moreover, we employ a joint optimization combining pretext tasks with contrastive learning to further enhance the spatio-temporal representation learning.
3rd Place: A Global and Local Dual Retrieval Solution to Facebook AI Image Similarity Challenge
As a basic task of computer vision, image similarity retrieval is facing the challenge of large-scale data and image copy attacks.
RIM: Reliable Influence-based Active Learning on Graphs
Message passing is the core of most graph models such as Graph Convolutional Network (GCN) and Label Propagation (LP), which usually require a large number of clean labeled data to smooth out the neighborhood over the graph.
Hot-Refresh Model Upgrades with Regression-Free Compatible Training in Image Retrieval
In contrast, hot-refresh model upgrades deploy the new model immediately and then gradually improve the retrieval accuracy by backfilling the gallery on-the-fly.
Grain: Improving Data Efficiency of Graph Neural Networks via Diversified Influence Maximization
Data selection methods, such as active learning and core-set selection, are useful tools for improving the data efficiency of deep learning models on large-scale datasets.
