B-GAP: Behavior-Guided Action Prediction for Autonomous Navigation

We present a novel learning algorithm for action prediction and local navigation for autonomous driving. Our approach classifies the driver behavior of other vehicles or road-agents (aggressive or conservative) and takes that into account for decision making and safe driving. We present a behavior-driven simulator that can generate trajectories corresponding to different levels of aggressive behaviors and use our simulator to train a policy using graph convolutional networks. We use a reinforcement learning-based navigation scheme that uses a proximity graph of traffic agents and computes a safe trajectory for the ego-vehicle that accounts for aggressive driver maneuvers such as overtaking, over-speeding, weaving, and sudden lane changes. We have integrated our algorithm with OpenAI gym-based "Highway-Env" simulator and demonstrate the benefits in terms of improved navigation in different scenarios.

BoMuDA: Boundless Multi-Source Domain Adaptive Segmentation in Unconstrained Environments

We present an unsupervised multi-source domain adaptive semantic segmentation approach in unstructured and unconstrained traffic environments. We propose a novel training strategy that alternates between single-source domain adaptation (DA) and multi-source distillation, and also between setting up an improvised cost function and optimizing it. In each iteration, the single-source DA first learns a neural network on a selected source, which is followed by a multi-source fine-tuning step using the remaining sources. We call this training routine the Alternating-Incremental ("Alt-Inc") algorithm. Furthermore, our approach is also boundless i.e. it can explicitly classify categories that do not belong to the training dataset (as opposed to labeling such objects as "unknown"). We have conducted extensive experiments and ablation studies using the Indian Driving Dataset, CityScapes, Berkeley DeepDrive, GTA V, and the Synscapes datasets, and we show that our unsupervised approach outperforms other unsupervised and semi-supervised SOTA benchmarks by 5.17% - 42.9% with a reduced model size by up to 5.2x.

Emotions Don't Lie: A Deepfake Detection Method using Audio-Visual Affective Cues

We present a learning-based multimodal method for detecting real and deepfake videos. To maximize information for learning, we extract and analyze the similarity between the two audio and visual modalities from within the same video. Additionally, we extract and compare affective cues corresponding to emotion from the two modalities within a video to infer whether the input video is "real" or "fake". We propose a deep learning network, inspired by the Siamese network architecture and the triplet loss. To validate our model, we report the AUC metric on two large-scale, audio-visual deepfake detection datasets, DeepFake-TIMIT Dataset and DFDC. We compare our approach with several SOTA deepfake detection methods and report per-video AUC of 84.4% on the DFDC and 96.6% on the DF-TIMIT datasets, respectively.

EmotiCon: Context-Aware Multimodal Emotion Recognition using Frege's Principle

We present EmotiCon, a learning-based algorithm for context-aware perceived human emotion recognition from videos and images. Motivated by Frege's Context Principle from psychology, our approach combines three interpretations of context for emotion recognition. Our first interpretation is based on using multiple modalities(e.g. faces and gaits) for emotion recognition. For the second interpretation, we gather semantic context from the input image and use a self-attention-based CNN to encode this information. Finally, we use depth maps to model the third interpretation related to socio-dynamic interactions and proximity among agents. We demonstrate the efficiency of our network through experiments on EMOTIC, a benchmark dataset. We report an Average Precision (AP) score of 35.48 across 26 classes, which is an improvement of 7-8 over prior methods. We also introduce a new dataset, GroupWalk, which is a collection of videos captured in multiple real-world settings of people walking. We report an AP of 65.83 across 4 categories on GroupWalk, which is also an improvement over prior methods.

CMetric: A Driving Behavior Measure Using Centrality Functions

We present a new measure, CMetric, to classify driver behaviors using centrality functions. Our formulation combines concepts from computational graph theory and social traffic psychology to quantify and classify the behavior of human drivers. CMetric is used to compute the probability of a vehicle executing a driving style, as well as the intensity used to execute the style. Our approach is designed for realtime autonomous driving applications, where the trajectory of each vehicle or road-agent is extracted from a video. We compute a dynamic geometric graph (DGG) based on the positions and proximity of the road-agents and centrality functions corresponding to closeness and degree. These functions are used to compute the CMetric based on style likelihood and style intensity estimates. Our approach is general and makes no assumption about traffic density, heterogeneity, or how driving behaviors change over time. We present efficient techniques to compute CMetric and demonstrate its performance on well-known autonomous driving datasets. We evaluate the accuracy of CMetric and compare with ground truth behavior labels and with that of a human observer by performing a user study over over a long vehicle trajectory.

DenseCAvoid: Real-time Navigation in Dense Crowds using Anticipatory Behaviors

We present DenseCAvoid, a novel navigation algorithm for navigating a robot through dense crowds and avoiding collisions by anticipating pedestrian behaviors. Our formulation uses visual sensors and a pedestrian trajectory prediction algorithm to track pedestrians in a set of input frames and provide bounding boxes that extrapolate the pedestrian positions in a future time. Our hybrid approach combines this trajectory prediction with a Deep Reinforcement Learning-based collision avoidance method to train a policy to generate smoother, safer, and more robust trajectories during run-time. We train our policy in realistic 3-D simulations of static and dynamic scenarios with multiple pedestrians. In practice, our hybrid approach generalizes well to unseen, real-world scenarios and can navigate a robot through dense crowds (~1-2 humans per square meter) in indoor scenarios, including narrow corridors and lobbies. As compared to cases where prediction was not used, we observe that our method reduces the occurrence of the robot freezing in a crowd by up to 48%, and performs comparably with respect to trajectory lengths and mean arrival times to goal.

Forecasting Trajectory and Behavior of Road-Agents Using Spectral Clustering in Graph-LSTMs

We present a novel approach for traffic forecasting in urban traffic scenarios using a combination of spectral graph analysis and deep learning. We predict both the low-level information (future trajectories) as well as the high-level information (road-agent behavior) from the extracted trajectory of each road-agent. Our formulation represents the proximity between the road agents using a dynamic weighted traffic-graph. We use a two-stream graph convolutional LSTM network to perform traffic forecasting using these weighted traffic-graphs. The first stream predicts the spatial coordinates of road-agents, while the second stream predicts whether a road-agent is going to exhibit aggressive, conservative, or normal behavior. We introduce spectral cluster regularization to reduce the error margin in long-term prediction (3-5 seconds) and improve the accuracy of the predicted trajectories. We evaluate our approach on the Argoverse, Lyft, and Apolloscape datasets and highlight the benefits over prior trajectory prediction methods. In practice, our approach reduces the average prediction error by more than 54% over prior algorithms and achieves a weighted average accuracy of 91.2% for behavior prediction.

M3ER: Multiplicative Multimodal Emotion Recognition Using Facial, Textual, and Speech Cues

We present M3ER, a learning-based method for emotion recognition from multiple input modalities. Our approach combines cues from multiple co-occurring modalities (such as face, text, and speech) and also is more robust than other methods to sensor noise in any of the individual modalities. M3ER models a novel, data-driven multiplicative fusion method to combine the modalities, which learn to emphasize the more reliable cues and suppress others on a per-sample basis. By introducing a check step which uses Canonical Correlational Analysis to differentiate between ineffective and effective modalities, M3ER is robust to sensor noise. M3ER also generates proxy features in place of the ineffectual modalities. We demonstrate the efficiency of our network through experimentation on two benchmark datasets, IEMOCAP and CMU-MOSEI. We report a mean accuracy of 82.7% on IEMOCAP and 89.0% on CMU-MOSEI, which, collectively, is an improvement of about 5% over prior work.

Take an Emotion Walk: Perceiving Emotions from Gaits Using Hierarchical Attention Pooling and Affective Mapping

We present an autoencoder-based semi-supervised approach to classify perceived human emotions from walking styles obtained from videos or from motion-captured data and represented as sequences of 3D poses. Given the motion on each joint in the pose at each time step extracted from 3D pose sequences, we hierarchically pool these joint motions in a bottom-up manner in the encoder, following the kinematic chains in the human body. We also constrain the latent embeddings of the encoder to contain the space of psychologically-motivated affective features underlying the gaits. We train the decoder to reconstruct the motions per joint per time step in a top-down manner from the latent embeddings. For the annotated data, we also train a classifier to map the latent embeddings to emotion labels. Our semi-supervised approach achieves a mean average precision of 0.84 on the Emotion-Gait benchmark dataset, which contains gaits collected from multiple sources. We outperform current state-of-art algorithms for both emotion recognition and action recognition from 3D gaits by 7% -- 23% on the absolute.

STEP: Spatial Temporal Graph Convolutional Networks for Emotion Perception from Gaits

We present a novel classifier network called STEP, to classify perceived human emotion from gaits, based on a Spatial Temporal Graph Convolutional Network (ST-GCN) architecture. Given an RGB video of an individual walking, our formulation implicitly exploits the gait features to classify the emotional state of the human into one of four emotions: happy, sad, angry, or neutral. We use hundreds of annotated real-world gait videos and augment them with thousands of annotated synthetic gaits generated using a novel generative network called STEP-Gen, built on an ST-GCN based Conditional Variational Autoencoder (CVAE). We incorporate a novel push-pull regularization loss in the CVAE formulation of STEP-Gen to generate realistic gaits and improve the classification accuracy of STEP. We also release a novel dataset (E-Gait), which consists of $2,177$ human gaits annotated with perceived emotions along with thousands of synthetic gaits. In practice, STEP can learn the affective features and exhibits classification accuracy of 89% on E-Gait, which is 14 - 30% more accurate over prior methods.