Peeking Into the Future: Predicting Future Person Activities and Locations in Videos
- Junwei Liang, Lu Jiang, Juan Carlos Niebles, A. Hauptmann, Li Fei-Fei
- Computer ScienceComputer Vision and Pattern Recognition
- 11 February 2019
An end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings is proposed, providing the first empirical evidence that joint modeling of paths and activities benefits future path prediction.
The Garden of Forking Paths: Towards Multi-Future Trajectory Prediction
- Junwei Liang, Lu Jiang, K. Murphy, Ting Yu, Alexander Hauptmann
- Computer ScienceComputer Vision and Pattern Recognition
- 13 December 2019
A new model to generate multiple plausible future trajectories, which contains novel designs of using multi-scale location encodings and convolutional RNNs over graphs, is introduced, referred to as Multiverse.
MSNet: A Multilevel Instance Segmentation Network for Natural Disaster Damage Assessment in Aerial Videos
- Xiaoyu Zhu, Junwei Liang, Alexander Hauptmann
- Computer ScienceIEEE Workshop/Winter Conference on Applications…
- 30 June 2020
A new model, namely MSNet, is presented, which contains novel region proposal network designs and an unsupervised score refinement network for confidence score calibration in both bounding box and mask branches and achieves state-of-the-art results compared to previous methods in this dataset.
Focal Visual-Text Attention for Visual Question Answering
- Junwei Liang, Lu Jiang, Liangliang Cao, Li-Jia Li, Alexander Hauptmann
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 1 June 2018
A novel neural network called Focal Visual-Text Attention network (FVTA) is described for collective reasoning in visual question answering, where both visual and text sequence information such as images and text metadata are presented.
Learning to Detect Concepts from Webly-Labeled Video Data
- Junwei Liang, Lu Jiang, Deyu Meng, Alexander Hauptmann
- Computer ScienceInternational Joint Conference on Artificial…
- 9 July 2016
This paper presents compelling insights on the latent non-convex robust loss that is being minimized on the noisy data and proposes two novel techniques that not only enable WELL to be applied to big data but also lead to more accurate results.
Peeking Into the Future: Predicting Future Person Activities and Locations in Videos
- Junwei Liang, Lu Jiang, Juan Carlos Niebles, Alexander Hauptmann, L. Fei-Fei
- Computer ScienceIEEE/CVF Conference on Computer Vision and…
- 1 June 2019
An end-to-end, multi-task learning system utilizing rich visual features about human behavioral information and interaction with their surroundings is proposed, providing the first empirical evidence that joint modeling of paths and activities benefits future path prediction.
MemexQA: Visual Memex Question Answering
- Lu Jiang, Junwei Liang, Liangliang Cao, Yannis Kalantidis, S. Farfade, Alexander Hauptmann
- Computer ScienceArXiv
- 4 August 2017
Experimental results on the MemexQA dataset demonstrate that MemexNet outperforms strong baselines and yields the state-of-the-art on this novel and challenging task, and suggest Memex net's efficacy and scalability across various QA tasks.
SimAug: Learning Robust Representations from Simulation for Trajectory Prediction
- Junwei Liang, Lu Jiang, A. Hauptmann
- Computer ScienceEuropean Conference on Computer Vision
- 4 April 2020
A novel approach to learn robust representation through augmenting the simulation training data such that the representation can better generalize to unseen real-world test data.
Minding the Gaps in a Video Action Analysis Pipeline
- Jia Chen, Jiang Liu, Alexander Hauptmann
- Computer ScienceIEEE Winter Applications of Computer Vision…
- 2019
An event detection system composed of four modules: feature extraction, event proposal generation, event classification and event localization is presented, which shares many similarities with standard object detection pipelines.
SimAug: Learning Robust Representations from 3D Simulation for Pedestrian Trajectory Prediction in Unseen Cameras
- Junwei Liang, Lu Jiang, Alexander Hauptmann
- Computer ScienceArXiv
- 4 April 2020
This paper proposes a method to efficiently utilize multi-view 3D simulation data for training that finds the hardest camera view to mix up with adversarial data from the original camera view in training, thus enabling the model to learn robust representations that can generalize to unseen camera views.
...
...