The CLIP (Contrastive Language-Image Pretraining) model has exhibited outstanding performance in recognition problems, such as zero-shot image classification and object detection. However, its ability to count remains understudied due to the inherent challenges of transforming counting--a regression task--into a recognition task. In this paper, we investigate CLIP's potential in counting, focusing specifically on estimating crowd sizes. Existing classification-based crowd-counting methods have encountered issues, including inappropriate discretization strategies, which impede the application of CLIP and result in suboptimal performance. To address these challenges, we propose the Enhanced Blockwise Classification (EBC) framework. In contrast to previous methods, EBC relies on integer-valued bins that facilitate the learning of robust decision boundaries. Within our model-agnostic EBC framework, we introduce CLIP-EBC, the first fully CLIP-based crowd-counting model capable of generating density maps. Comprehensive evaluations across diverse crowd-counting datasets demonstrate the state-of-the-art performance of our methods. Particularly, EBC can improve existing models by up to 76.9%. Moreover, our CLIP-EBC model surpasses current crowd-counting methods, achieving mean absolute errors of 55.0 and 6.3 on ShanghaiTech part A and part B datasets, respectively. The code will be made publicly available.
While depression has been studied via multimodal non-verbal behavioural cues, head motion behaviour has not received much attention as a biomarker. This study demonstrates the utility of fundamental head-motion units, termed \emph{kinemes}, for depression detection by adopting two distinct approaches, and employing distinctive features: (a) discovering kinemes from head motion data corresponding to both depressed patients and healthy controls, and (b) learning kineme patterns only from healthy controls, and computing statistics derived from reconstruction errors for both the patient and control classes. Employing machine learning methods, we evaluate depression classification performance on the \emph{BlackDog} and \emph{AVEC2013} datasets. Our findings indicate that: (1) head motion patterns are effective biomarkers for detecting depressive symptoms, and (2) explanatory kineme patterns consistent with prior findings can be observed for the two classes. Overall, we achieve peak F1 scores of 0.79 and 0.82, respectively, over BlackDog and AVEC2013 for binary classification over episodic \emph{thin-slices}, and a peak F1 of 0.72 over videos for AVEC2013.
Driver Monitoring Systems (DMSs) are crucial for safe hand-over actions in Level-2+ self-driving vehicles. State-of-the-art DMSs leverage multiple sensors mounted at different locations to monitor the driver and the vehicle's interior scene and employ decision-level fusion to integrate these heterogenous data. However, this fusion method may not fully utilize the complementarity of different data sources and may overlook their relative importance. To address these limitations, we propose a novel multiview multimodal driver monitoring system based on feature-level fusion through multi-head self-attention (MHSA). We demonstrate its effectiveness by comparing it against four alternative fusion strategies (Sum, Conv, SE, and AFF). We also present a novel GPU-friendly supervised contrastive learning framework SuMoCo to learn better representations. Furthermore, We fine-grained the test split of the DAD dataset to enable the multi-class recognition of drivers' activities. Experiments on this enhanced database demonstrate that 1) the proposed MHSA-based fusion method (AUC-ROC: 97.0\%) outperforms all baselines and previous approaches, and 2) training MHSA with patch masking can improve its robustness against modality/view collapses. The code and annotations are publicly available.
Heterogeneous graphs provide a compact, efficient, and scalable way to model data involving multiple disparate modalities. This makes modeling audiovisual data using heterogeneous graphs an attractive option. However, graph structure does not appear naturally in audiovisual data. Graphs for audiovisual data are constructed manually which is both difficult and sub-optimal. In this work, we address this problem by (i) proposing a parametric graph construction strategy for the intra-modal edges, and (ii) learning the crossmodal edges. To this end, we develop a new model, heterogeneous graph crossmodal network (HGCN) that learns the crossmodal edges. Our proposed model can adapt to various spatial and temporal scales owing to its parametric construction, while the learnable crossmodal edges effectively connect the relevant nodes across modalities. Experiments on a large benchmark dataset (AudioSet) show that our model is state-of-the-art (0.53 mean average precision), outperforming transformer-based models and other graph-based models.
We explore the efficacy of multimodal behavioral cues for explainable prediction of personality and interview-specific traits. We utilize elementary head-motion units named kinemes, atomic facial movements termed action units and speech features to estimate these human-centered traits. Empirical results confirm that kinemes and action units enable discovery of multiple trait-specific behaviors while also enabling explainability in support of the predictions. For fusing cues, we explore decision and feature-level fusion, and an additive attention-based fusion strategy which quantifies the relative importance of the three modalities for trait prediction. Examining various long-short term memory (LSTM) architectures for classification and regression on the MIT Interview and First Impressions Candidate Screening (FICS) datasets, we note that: (1) Multimodal approaches outperform unimodal counterparts; (2) Efficient trait predictions and plausible explanations are achieved with both unimodal and multimodal approaches, and (3) Following the thin-slice approach, effective trait prediction is achieved even from two-second behavioral snippets.
Driver distractions are known to be the dominant cause of road accidents. While monitoring systems can detect non-driving-related activities and facilitate reducing the risks, they must be accurate and efficient to be applicable. Unfortunately, state-of-the-art methods prioritize accuracy while ignoring latency because they leverage cross-view and multimodal videos in which consecutive frames are highly similar. Thus, in this paper, we pursue time-effective detection models by neglecting the temporal relation between video frames and investigate the importance of each sensing modality in detecting drives' activities. Experiments demonstrate that 1) our proposed algorithms are real-time and can achieve similar performances (97.5\% AUC-PR) with significantly reduced computation compared with video-based models; 2) the top view with the infrared channel is more informative than any other single modality. Furthermore, we enhance the DAD dataset by manually annotating its test set to enable multiclassification. We also thoroughly analyze the influence of visual sensor types and their placements on the prediction of each class. The code and the new labels will be released.
Active speaker detection (ASD) in videos with multiple speakers is a challenging task as it requires learning effective audiovisual features and spatial-temporal correlations over long temporal windows. In this paper, we present SPELL, a novel spatial-temporal graph learning framework that can solve complex tasks such as ASD. To this end, each person in a video frame is first encoded in a unique node for that frame. Nodes corresponding to a single person across frames are connected to encode their temporal dynamics. Nodes within a frame are also connected to encode inter-person relationships. Thus, SPELL reduces ASD to a node classification task. Importantly, SPELL is able to reason over long temporal contexts for all nodes without relying on computationally expensive fully connected graph neural networks. Through extensive experiments on the AVA-ActiveSpeaker dataset, we demonstrate that learning graph-based representations can significantly improve the active speaker detection performance owing to its explicit spatial and temporal structure. SPELL outperforms all previous state-of-the-art approaches while requiring significantly lower memory and computational resources. Our code is publicly available at https://github.com/SRA2/SPELL
Perception of auditory events is inherently multimodal relying on both audio and visual cues. A large number of existing multimodal approaches process each modality using modality-specific models and then fuse the embeddings to encode the joint information. In contrast, we employ heterogeneous graphs to explicitly capture the spatial and temporal relationships between the modalities and represent detailed information about the underlying signal. Using heterogeneous graph approaches to address the task of visually-aware acoustic event classification, which serves as a compact, efficient and scalable way to represent data in the form of graphs. Through heterogeneous graphs, we show efficiently modelling of intra- and inter-modality relationships both at spatial and temporal scales. Our model can easily be adapted to different scales of events through relevant hyperparameters. Experiments on AudioSet, a large benchmark, shows that our model achieves state-of-the-art performance.