Video captioning models have seen notable advancements in recent years, especially with regard to their ability to capture temporal information. While many research efforts have focused on architectural advancements, such as temporal attention mechanisms, there remains a notable gap in understanding how models capture and utilize temporal semantics for effective temporal feature extraction, especially in the context of Advanced Driver Assistance Systems. We propose an automated LiDAR-based captioning procedure that focuses on the temporal dynamics of traffic participants. Our approach uses a rule-based system to extract essential details such as lane position and relative motion from object tracks, followed by a template-based caption generation. Our findings show that training SwinBERT, a video captioning model, using only front camera images and supervised with our template-based captions, specifically designed to encapsulate fine-grained temporal behavior, leads to improved temporal understanding consistently across three datasets. In conclusion, our results clearly demonstrate that integrating LiDAR-based caption supervision significantly enhances temporal understanding, effectively addressing and reducing the inherent visual/static biases prevalent in current state-of-the-art model architectures.

Abstract Object detection on Lidar point cloud data is a promising technology for autonomous driving and robotics which has seen a significant rise in performance and accuracy during recent years. Particularly uncertainty estimation is a crucial component for down-stream tasks and deep neural networks remain error-prone even for predictions with high confidence. Previously proposed methods for quantifying prediction uncertainty tend to alter the training scheme of the detector or rely on prediction sampling which results in vastly increased inference time. In order to address these two issues, we propose LidarMetaDetect (LMD), a light-weight post-processing scheme for prediction quality estimation. Our method can easily be added to any pre-trained Lidar object detector without altering anything about the base model and is purely based on post-processing, therefore, only leading to a negligible computational overhead. Our experiments show a significant increase of statistical reliability in separating true from false predictions. We show that this improvement carries over to object detection performance when replacing the objectness score native to the object detector. We propose and evaluate an additional application of our method leading to the detection of annotation errors. Explicit samples and a conservative count of annotation error proposals indicates the viability of our method for large-scale datasets like KITTI and nuScenes. On the widely-used nuScenes test dataset, 43 out of the top 100 proposals of our method indicate, in fact, erroneous annotations.

Today, comparing audio watermarking systems remain a challenge due to the lack of publicly-available reference algorithms. In addition, robustness against acoustic path transmission is only occasionally evaluated. This jeopardizes the chances of digital watermarking to be adopted in the context of applications where such a feature is vital, e.g., second screen, audience measurement, and so on. In this paper, we introduce a rather simple audio watermarking algorithm, whose source code has been publicized for potential reuse by the watermarking community. We then complement this baseline system with three additional components, namely a psychoacoustic model, a resynchronization framework, and an improved correlation-based detector. Reported experimental results clearly demonstrate that the resulting high-fidelity audio watermarking system manages to survive the acoustic path.

The weighted overlap add (WOLA) technique is routinely used in audio processing to avoid introducing audible clicks. This process introduces inter-dependencies between WOLA coefficients and it is thus necessary to revisit watermarking algorithms to accommodate for such dependencies and prevent introducing self-inflicted interferences. In this paper, we focus on an existing phase quantization based audio watermarking system. Instead of the original computationally expensive ad-hoc process for dealing with the inter dependencies between WOLA coefficients, we introduce an alternative strategy. Experimental results show a notable reduction of the complexity while maintaining robustness performances.

In this industrial exhibit, Technicolor will showcase various technologies developed to protect digital audio-visual material all along the media value chain, from production to distribution, including forensics services in case pirated content is detected. The exhibit will be organized around Technicolor's proprietary technologies in video fingerprinting and audio/video watermarking.