Jia Huang

Jia Huang, Peng Jiang, Alvika Gautam et al.

Predicting pedestrian behavior is the key to ensure safety and reliability of autonomous vehicles. While deep learning methods have been promising by learning from annotated video frame sequences, they often fail to fully grasp the dynamic interactions between pedestrians and traffic, crucial for accurate predictions. These models also lack nuanced common sense reasoning. Moreover, the manual annotation of datasets for these models is expensive and challenging to adapt to new situations. The advent of Vision Language Models (VLMs) introduces promising alternatives to these issues, thanks to their advanced visual and causal reasoning skills. To our knowledge, this research is the first to conduct both quantitative and qualitative evaluations of VLMs in the context of pedestrian behavior prediction for autonomous driving. We evaluate GPT-4V(ision) on publicly available pedestrian datasets: JAAD and WiDEVIEW. Our quantitative analysis focuses on GPT-4V's ability to predict pedestrian behavior in current and future frames. The model achieves a 57% accuracy in a zero-shot manner, which, while impressive, is still behind the state-of-the-art domain-specific models (70%) in predicting pedestrian crossing actions. Qualitatively, GPT-4V shows an impressive ability to process and interpret complex traffic scenarios, differentiate between various pedestrian behaviors, and detect and analyze groups. However, it faces challenges, such as difficulty in detecting smaller pedestrians and assessing the relative motion between pedestrians and the ego vehicle.

Alex Kim, Jia Huang, Rob Monarch et al.

Application developers advertise their Apps by creating product pages with App images, and bidding on search terms. It is then crucial for App images to be highly relevant with the search terms. Solutions to this problem require an image-text matching model to predict the quality of the match between the chosen image and the search terms. In this work, we present a novel approach to matching an App image to search terms based on fine-tuning a pre-trained LXMERT model. We show that compared to the CLIP model and a baseline using a Transformer model for search terms, and a ResNet model for images, we significantly improve the matching accuracy. We evaluate our approach using two sets of labels: advertiser associated (image, search term) pairs for a given application, and human ratings for the relevance between (image, search term) pairs. Our approach achieves 0.96 AUC score for advertiser associated ground truth, outperforming the transformer+ResNet baseline and the fine-tuned CLIP model by 8% and 14%. For human labeled ground truth, our approach achieves 0.95 AUC score, outperforming the transformer+ResNet baseline and the fine-tuned CLIP model by 16% and 17%.

Jia Huang, Alvika Gautam, Srikanth Saripalli

To ensure safe autonomous driving in urban environments with complex vehicle-pedestrian interactions, it is critical for Autonomous Vehicles (AVs) to have the ability to predict pedestrians' short-term and immediate actions in real-time. In recent years, various methods have been developed to study estimating pedestrian behaviors for autonomous driving scenarios, but there is a lack of clear definitions for pedestrian behaviors. In this work, the literature gaps are investigated and a taxonomy is presented for pedestrian behavior characterization. Further, a novel multi-task sequence to sequence Transformer encoders-decoders (TF-ed) architecture is proposed for pedestrian action and trajectory prediction using only ego vehicle camera observations as inputs. The proposed approach is compared against an existing LSTM encoders decoders (LSTM-ed) architecture for action and trajectory prediction. The performance of both models is evaluated on the publicly available Joint Attention Autonomous Driving (JAAD) dataset, CARLA simulation data as well as real-time self-driving shuttle data collected on university campus. Evaluation results illustrate that the proposed method reaches an accuracy of 81% on action prediction task on JAAD testing data and outperforms the LSTM-ed by 7.4%, while LSTM counterpart performs much better on trajectory prediction task for a prediction sequence length of 25 frames.

Jinwoo Choi, Chen Gao, Joseph C. E. Messou et al.

Human activities often occur in specific scene contexts, e.g., playing basketball on a basketball court. Training a model using existing video datasets thus inevitably captures and leverages such bias (instead of using the actual discriminative cues). The learned representation may not generalize well to new action classes or different tasks. In this paper, we propose to mitigate scene bias for video representation learning. Specifically, we augment the standard cross-entropy loss for action classification with 1) an adversarial loss for scene types and 2) a human mask confusion loss for videos where the human actors are masked out. These two losses encourage learning representations that are unable to predict the scene types and the correct actions when there is no evidence. We validate the effectiveness of our method by transferring our pre-trained model to three different tasks, including action classification, temporal localization, and spatio-temporal action detection. Our results show consistent improvement over the baseline model without debiasing.