Temporally grounding natural sentence in video
We introduce an effective and efficient method that grounds (ie, localizes) natural sentences
in long, untrimmed video sequences. Specifically, a novel Temporal GroundNet (TGN) is …
in long, untrimmed video sequences. Specifically, a novel Temporal GroundNet (TGN) is …
Computational understanding of visual interestingness beyond semantics: literature survey and analysis of covariates
Understanding visual interestingness is a challenging task addressed by researchers in
various disciplines ranging from humanities and psychology to, more recently, computer …
various disciplines ranging from humanities and psychology to, more recently, computer …
CBR: context bias aware recommendation for debiasing user modeling and click prediction
With the prosperity of recommender systems, the biases existing in user behaviors, which
may lead to inconsistency between user preference and behavior records, have attracted …
may lead to inconsistency between user preference and behavior records, have attracted …
Sending or not? A multimodal framework for Danmaku comment prediction
D Xi, W Xu, R Chen, Y Zhou, Z Yang - Information Processing & …, 2021 - Elsevier
Danmaku is an emerging comment design for videos that allows real-time, interactive
comments from viewers. Danmaku increases viewers' interaction with other viewers and …
comments from viewers. Danmaku increases viewers' interaction with other viewers and …
On the consensus of synchronous temporal and spatial views: A novel multimodal deep learning method for social video prediction
The blowout development of video social platforms has spawned a wide range of social
video prediction (SVP) tasks, such as video attractiveness prediction and video sentiment …
video prediction (SVP) tasks, such as video attractiveness prediction and video sentiment …
Predicting video engagement using heterogeneous DeepWalk
I Chaturvedi, K Thapa, S Cavallari, E Cambria… - Neurocomputing, 2021 - Elsevier
Video engagement is important in online advertisements where there is no physical
interaction with the consumer. Engagement can be directly measured as the number of …
interaction with the consumer. Engagement can be directly measured as the number of …
Non-local netvlad encoding for video classification
This paper describes our solution for the 2nd YouTube-8M video understanding challenge
organized by Google AI. Unlike the video recognition benchmarks, such as Kinetics and …
organized by Google AI. Unlike the video recognition benchmarks, such as Kinetics and …
Bidirectional image-sentence retrieval by local and global deep matching
In this paper, we propose a novel local and global deep matching model to tackle
bidirectional image-sentence retrieval. Our proposed matching model can simultaneously …
bidirectional image-sentence retrieval. Our proposed matching model can simultaneously …
Parsimonious quantile regression of financial asset tail dynamics via sequential learning
We propose a parsimonious quantile regression framework to learn the dynamic tail
behaviors of financial asset returns. Our model captures well both the time-varying …
behaviors of financial asset returns. Our model captures well both the time-varying …
Multi-branch LSTM encoded latent features with CNN-LSTM for Youtube popularity prediction
N Sangwan, V Bhatnagar - Scientific Reports, 2025 - nature.com
As digital media grows, there is an increasing demand for engaging content that can
captivate audiences. Along with that, the monetary conversion of those engaging videos is …
captivate audiences. Along with that, the monetary conversion of those engaging videos is …