Abstract:Extensions of Neural Radiance Fields (NeRFs) to model dynamic scenes have enabled their near photo-realistic, free-viewpoint rendering. Although these methods have shown some potential in creating immersive experiences, two drawbacks limit their ubiquity: (i) a significant reduction in reconstruction quality when the computing budget is limited, and (ii) a lack of semantic understanding of the underlying scenes. To address these issues, we introduce Gear-NeRF, which leverages semantic information from powerful image segmentation models. Our approach presents a principled way for learning a spatio-temporal (4D) semantic embedding, based on which we introduce the concept of gears to allow for stratified modeling of dynamic regions of the scene based on the extent of their motion. Such differentiation allows us to adjust the spatio-temporal sampling resolution for each region in proportion to its motion scale, achieving more photo-realistic dynamic novel view synthesis. At the same time, almost for free, our approach enables free-viewpoint tracking of objects of interest - a functionality not yet achieved by existing NeRF-based methods. Empirical studies validate the effectiveness of our method, where we achieve state-of-the-art rendering and tracking performance on multiple challenging datasets.
Abstract:The primary bottleneck towards obtaining good recognition performance in IR images is the lack of sufficient labeled training data, owing to the cost of acquiring such data. Realizing that object detection methods for the RGB modality are quite robust (at least for some commonplace classes, like person, car, etc.), thanks to the giant training sets that exist, in this work we seek to leverage cues from the RGB modality to scale object detectors to the IR modality, while preserving model performance in the RGB modality. At the core of our method, is a novel tensor decomposition method called TensorFact which splits the convolution kernels of a layer of a Convolutional Neural Network (CNN) into low-rank factor matrices, with fewer parameters than the original CNN. We first pretrain these factor matrices on the RGB modality, for which plenty of training data are assumed to exist and then augment only a few trainable parameters for training on the IR modality to avoid over-fitting, while encouraging them to capture complementary cues from those trained only on the RGB modality. We validate our approach empirically by first assessing how well our TensorFact decomposed network performs at the task of detecting objects in RGB images vis-a-vis the original network and then look at how well it adapts to IR images of the FLIR ADAS v1 dataset. For the latter, we train models under scenarios that pose challenges stemming from data paucity. From the experiments, we observe that: (i) TensorFact shows performance gains on RGB images; (ii) further, this pre-trained model, when fine-tuned, outperforms a standard state-of-the-art object detector on the FLIR ADAS v1 dataset by about 4% in terms of mAP 50 score.
Abstract:Efficient navigation towards an audio-goal necessitates an embodied agent to not only possess the ability to use audio-visual cues effectively, but also be equipped to actively (but occasionally) seek human/oracle assistance without sacrificing autonomy, e.g., when it is uncertain of where to navigate towards locating a noisy or sporadic audio goal. To this end, we present CAVEN -- a conversational audio-visual embodied navigation agent that is capable of posing navigation questions to a human/oracle and processing the oracle responses; both in free-form natural language. At the core of CAVEN is a multimodal hierarchical reinforcement learning (RL) setup that is equipped with a high-level policy that is trained to choose from one of three low-level policies (at every step), namely: (i) to navigate using audio-visual cues, or (ii) to frame a question to the oracle and receive a short or detailed response, or (iii) ask generic questions (when unsure of what to ask) and receive instructions. Key to generating the agent's questions is our novel TrajectoryNet that forecasts the most likely next steps to the goal and a QuestionNet that uses these steps to produce a question. All the policies are learned end-to-end via the RL setup, with penalties to enforce sparsity in receiving navigation instructions from the oracle. To evaluate the performance of CAVEN, we present extensive experiments on the SoundSpaces framework for the task of semantic audio-visual navigation. Our results show that CAVEN achieves upto 12% gain in performance over competing methods, especially in localizing new sound sources, even in the presence of auditory distractions.
Abstract:There exists an unequivocal distinction between the sound produced by a static source and that produced by a moving one, especially when the source moves towards or away from the microphone. In this paper, we propose to use this connection between audio and visual dynamics for solving two challenging tasks simultaneously, namely: (i) separating audio sources from a mixture using visual cues, and (ii) predicting the 3D visual motion of a sounding source using its separated audio. Towards this end, we present Audio Separator and Motion Predictor (ASMP) -- a deep learning framework that leverages the 3D structure of the scene and the motion of sound sources for better audio source separation. At the heart of ASMP is a 2.5D scene graph capturing various objects in the video and their pseudo-3D spatial proximities. This graph is constructed by registering together 2.5D monocular depth predictions from the 2D video frames and associating the 2.5D scene regions with the outputs of an object detector applied on those frames. The ASMP task is then mathematically modeled as the joint problem of: (i) recursively segmenting the 2.5D scene graph into several sub-graphs, each associated with a constituent sound in the input audio mixture (which is then separated) and (ii) predicting the 3D motions of the corresponding sound sources from the separated audio. To empirically evaluate ASMP, we present experiments on two challenging audio-visual datasets, viz. Audio Separation in the Wild (ASIW) and Audio Visual Event (AVE). Our results demonstrate that ASMP achieves a clear improvement in source separation quality, outperforming prior works on both datasets, while also estimating the direction of motion of the sound sources better than other methods.
Abstract:Predicting the future frames of a video is a challenging task, in part due to the underlying stochastic real-world phenomena. Prior approaches to solve this task typically estimate a latent prior characterizing this stochasticity, however do not account for the predictive uncertainty of the (deep learning) model. Such approaches often derive the training signal from the mean-squared error (MSE) between the generated frame and the ground truth, which can lead to sub-optimal training, especially when the predictive uncertainty is high. Towards this end, we introduce Neural Uncertainty Quantifier (NUQ) - a stochastic quantification of the model's predictive uncertainty, and use it to weigh the MSE loss. We propose a hierarchical, variational framework to derive NUQ in a principled manner using a deep, Bayesian graphical model. Our experiments on four benchmark stochastic video prediction datasets show that our proposed framework trains more effectively compared to the state-of-the-art models (especially when the training sets are small), while demonstrating better video generation quality and diversity against several evaluation metrics.
Abstract:State-of-the-art approaches for visually-guided audio source separation typically assume sources that have characteristic sounds, such as musical instruments. These approaches often ignore the visual context of these sound sources or avoid modeling object interactions that may be useful to better characterize the sources, especially when the same object class may produce varied sounds from distinct interactions. To address this challenging problem, we propose Audio Visual Scene Graph Segmenter (AVSGS), a novel deep learning model that embeds the visual structure of the scene as a graph and segments this graph into subgraphs, each subgraph being associated with a unique sound obtained by co-segmenting the audio spectrogram. At its core, AVSGS uses a recursive neural network that emits mutually-orthogonal sub-graph embeddings of the visual graph using multi-head attention. These embeddings are used for conditioning an audio encoder-decoder towards source separation. Our pipeline is trained end-to-end via a self-supervised task consisting of separating audio sources using the visual graph from artificially mixed sounds. In this paper, we also introduce an "in the wild'' video dataset for sound source separation that contains multiple non-musical sources, which we call Audio Separation in the Wild (ASIW). This dataset is adapted from the AudioCaps dataset, and provides a challenging, natural, and daily-life setting for source separation. Thorough experiments on the proposed ASIW and the standard MUSIC datasets demonstrate state-of-the-art sound separation performance of our method against recent prior approaches.
Abstract:Learning associations across modalities is critical for robust multimodal reasoning, especially when a modality may be missing during inference. In this paper, we study this problem in the context of audio-conditioned visual synthesis -- a task that is important, for example, in occlusion reasoning. Specifically, our goal is to generate future video frames and their motion dynamics conditioned on audio and a few past frames. To tackle this problem, we present Sound2Sight, a deep variational framework, that is trained to learn a per frame stochastic prior conditioned on a joint embedding of audio and past frames. This embedding is learned via a multi-head attention-based audio-visual transformer encoder. The learned prior is then sampled to further condition a video forecasting module to generate future frames. The stochastic prior allows the model to sample multiple plausible futures that are consistent with the provided audio and the past context. Moreover, to improve the quality and coherence of the generated frames, we propose a multimodal discriminator that differentiates between a synthesized and a real audio-visual clip. We empirically evaluate our approach, vis-\'a-vis closely-related prior methods, on two new datasets viz. (i) Multimodal Stochastic Moving MNIST with a Surprise Obstacle, (ii) Youtube Paintings; as well as on the existing Audio-Set Drums dataset. Our extensive experiments demonstrate that Sound2Sight significantly outperforms the state of the art in the generated video quality, while also producing diverse video content.
Abstract:Paragraph generation from images, which has gained popularity recently, is an important task for video summarization, editing, and support of the disabled. Traditional image captioning methods fall short on this front, since they aren't designed to generate long informative descriptions. Moreover, the vanilla approach of simply concatenating multiple short sentences, possibly synthesized from a classical image captioning system, doesn't embrace the intricacies of paragraphs: coherent sentences, globally consistent structure, and diversity. To address those challenges, we propose to augment paragraph generation techniques with 'coherence vectors', 'global topic vectors', and modeling of the inherent ambiguity of associating paragraphs with images, via a variational auto-encoder formulation. We demonstrate the effectiveness of the developed approach on two datasets, outperforming existing state-of-the-art techniques on both.
Abstract:We propose a novel Convolutional Neural Network (CNN) compression algorithm based on coreset representations of filters. We exploit the redundancies extant in the space of CNN weights and neuronal activations (across samples) in order to obtain compression. Our method requires no retraining, is easy to implement, and obtains state-of-the-art compression performance across a wide variety of CNN architectures. Coupled with quantization and Huffman coding, we create networks that provide AlexNet-like accuracy, with a memory footprint that is $832\times$ smaller than the original AlexNet, while also introducing significant reductions in inference time as well. Additionally these compressed networks when fine-tuned, successfully generalize to other domains as well.
Abstract:Conventional multimedia annotation/retrieval systems such as Normalized Continuous Relevance Model (NormCRM) [16] require a fully labeled training data for a good performance. Active Learning, by determining an order for labeling the training data, allows for a good performance even before the training data is fully annotated. In this work we propose an active learning algorithm, which combines a novel measure of sample uncertainty with a novel clustering-based approach for determining sample density and diversity and integrate it with NormCRM. The clusters are also iteratively refined to ensure both feature and label-level agreement among samples. We show that our approach outperforms multiple baselines both on a recent, open character animation dataset and on the popular TRECVID corpus at both the tasks of annotation and text-based retrieval of videos.