Bifold and semantic reasoning for pedestrian behavior prediction
Pedestrian behavior prediction is one of the major challenges for intelligent driving systems.
Pedestrians often exhibit complex behaviors influenced by various contextual elements. To …
Pedestrians often exhibit complex behaviors influenced by various contextual elements. To …
Deep learning for vision-based prediction: A survey
A Rasouli - arXiv preprint arXiv:2007.00095, 2020 - arxiv.org
Vision-based prediction algorithms have a wide range of applications including autonomous
driving, surveillance, human-robot interaction, weather prediction. The objective of this …
driving, surveillance, human-robot interaction, weather prediction. The objective of this …
Multi-modal hybrid architecture for pedestrian action prediction
Pedestrian behavior prediction is one of the major challenges for intelligent driving systems
in urban environments. Pedestrians often exhibit a wide range of behaviors and adequate …
in urban environments. Pedestrians often exhibit a wide range of behaviors and adequate …
PedFormer: Pedestrian behavior prediction via cross-modal attention modulation and gated multitask learning
A Rasouli, I Kotseruba - 2023 IEEE International Conference on …, 2023 - ieeexplore.ieee.org
Predicting pedestrian behavior is a crucial task for intelligent driving systems. Accurate
predictions require a deep understanding of various contextual elements that could impact …
predictions require a deep understanding of various contextual elements that could impact …
Learning to sit: Synthesizing human-chair interactions via hierarchical control
Recent progress on physics-based character animation has shown impressive
breakthroughs on human motion synthesis, through imitating motion capture data via deep …
breakthroughs on human motion synthesis, through imitating motion capture data via deep …
Intent prediction in human–human interactions
The human ability to infer others' intent is innate and crucial to development. Machines
ought to acquire this ability for seamless interaction with humans. In this article, we propose …
ought to acquire this ability for seamless interaction with humans. In this article, we propose …
Receptive multi-granularity representation for person re-identification
A key for person re-identification is achieving consistent local details for discriminative
representation across variable environments. Current stripe-based feature learning …
representation across variable environments. Current stripe-based feature learning …
Recurrent semantic preserving generation for action prediction
In this paper, we propose a recurrent semantic preserving generation (RSPG) method for
action prediction. Unlike most existing methods which don't make full use of information from …
action prediction. Unlike most existing methods which don't make full use of information from …
Group activity prediction with sequential relational anticipation model
In this paper, we propose a novel approach to predict group activities given the beginning
frames with incomplete activity executions. Existing action (We define action as the behavior …
frames with incomplete activity executions. Existing action (We define action as the behavior …
Where to look: Multi-granularity occlusion aware for video person re-identification
Video person re-identification (re-ID) plays an important role in intelligent video surveillance,
which can automatically match the same person across video clips under non-overlapping …
which can automatically match the same person across video clips under non-overlapping …