Why do we click: visual impression-aware news recommendation

J Xun, S Zhang, Z Zhao, J Zhu, Q Zhang, J Li… - Proceedings of the 29th …, 2021 - dl.acm.org
There is a soaring interest in the news recommendation research scenario due to the
information overload. To accurately capture users' interests, we propose to model multi …

A roadmap for big model

S Yuan, H Zhao, S Zhao, J Leng, Y Liang… - arxiv preprint arxiv …, 2022 - arxiv.org
With the rapid development of deep learning, training Big Models (BMs) for multiple
downstream tasks becomes a popular paradigm. Researchers have achieved various …

Where did i leave my keys?-episodic-memory-based question answering on egocentric videos

L Bärmann, A Waibel - … of the IEEE/CVF Conference on …, 2022 - openaccess.thecvf.com
Humans have a remarkable ability to organize, compress and retrieve episodic memories
throughout their daily life. Current AI systems, however, lack comparable capabilities as they …

Grounded Question-Answering in Long Egocentric Videos

S Di, W **e - Proceedings of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Existing approaches to video understanding mainly designed for short videos from a third-
person perspective are limited in their applicability in certain fields such as robotics. In this …

Encode-Store-Retrieve: Enhancing Memory Augmentation through Language-Encoded Egocentric Perception

J Shen, J Dudley, PO Kristensson - arxiv preprint arxiv:2308.05822, 2023 - arxiv.org
We depend on our own memory to encode, store, and retrieve our experiences. However,
memory lapses can occur. One promising avenue for achieving memory augmentation is …

A memory model for question answering from streaming data supported by rehearsal and anticipation of coreference information

V Araujo, A Soto, MF Moens - arxiv preprint arxiv:2305.07565, 2023 - arxiv.org
Existing question answering methods often assume that the input content (eg, documents or
videos) is always accessible to solve the task. Alternatively, memory networks were …

Taohighlight: Commodity-aware multi-modal video highlight detection in e-commerce

Z Guo, Z Zhao, W **, D Wang, R Liu… - IEEE Transactions on …, 2021 - ieeexplore.ieee.org
In e-commerce, product related video is important content to introduce product
characteristics and attract consumers. Especially in the recommendation system of e …

Track-On: Transformer-based Online Point Tracking with Memory

G Aydemir, X Cai, W **e, F Güney - arxiv preprint arxiv:2501.18487, 2025 - arxiv.org
In this paper, we consider the problem of long-term point tracking, which requires consistent
identification of points across multiple frames in a video, despite changes in appearance …

Encode-Store-Retrieve: Augmenting Human Memory through Language-Encoded Egocentric Perception

J Shen, JJ Dudley… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
We depend on our own memory to encode, store, and retrieve our experiences. However,
memory lapses can occur. One promising avenue for achieving memory augmentation is …

Dual Memory Structure for Memory Augmented Neural Networks for Question-Answering Tasks

A Bidokhti, S Ghaemmaghami - 2022 12th International …, 2022 - ieeexplore.ieee.org
Memory is crucial for machine learning tasks on sequential data. From vanilla RNN to LSTM
and memory augmented neural networks, researchers have investigated several types of …