Large language models (LLMs), pre-trained on vast amounts of text, have shown remarkable abilities in understanding general knowledge and commonsense. There-fore, it's desirable to leverage pre-trained LLM to help solve computer vision tasks. Previous works on multi-modal LLM mainly focus on the generation capability. In this work, we propose LLM-augmented visual representation learning (LMVR). Our approach involves initially using a vision encoder to extract features, which are then projected into the word embedding space of the LLM. The LLM then generates responses based on the visual representation and a text prompt. Finally, we aggregate sequence-level features from the hidden layers of the LLM to obtain image-level representations. We conduct extensive experiments on multiple datasets, and have the following findings: (a) LMVR outperforms traditional vision encoder on various down-stream tasks, and effectively learns the correspondence between words and image regions; (b) LMVR improves the generalizability compared to using a vision encoder alone, as evidenced by its superior resistance to domain shift; (c) LMVR improves the robustness of models to corrupted and perturbed visual data. Our findings demonstrate LLM-augmented visual representation learning is effective as it learns object-level concepts and commonsense knowledge.

Co-speech gestures are a key channel of human communication, making them important for personalized chat agents to generate. In the past, gesture generation models assumed that data for each speaker is available all at once, and in large amounts. However in practical scenarios, speaker data comes sequentially and in small amounts as the agent personalizes with more speakers, akin to a continual learning paradigm. While more recent works have shown progress in adapting to low-resource data, they catastrophically forget the gesture styles of initial speakers they were trained on. Also, prior generative continual learning works are not multimodal, making this space less studied. In this paper, we explore this new paradigm and propose C-DiffGAN: an approach that continually learns new speaker gesture styles with only a few minutes of per-speaker data, while retaining previously learnt styles. Inspired by prior continual learning works, C-DiffGAN encourages knowledge retention by 1) generating reminiscences of previous low-resource speaker data, then 2) crossmodally aligning to them to mitigate catastrophic forgetting. We quantitatively demonstrate improved performance and reduced forgetting over strong baselines through standard continual learning measures, reinforced by a qualitative user study that shows that our method produces more natural, style-preserving gestures. Code and videos can be found at https://chahuja.com/cdiffgan

Many educational videos use slide presentations, a sequence of visual pages that contain text and figures accompanied by spoken language, which are constructed and presented carefully in order to optimally transfer knowledge to students. Previous studies in multimedia and psychology attribute the effectiveness of lecture presentations to their multimodal nature. As a step toward developing vision-language models to aid in student learning as intelligent teacher assistants, we introduce the Lecture Presentations Multimodal (LPM) Dataset as a large-scale benchmark testing the capabilities of vision-and-language models in multimodal understanding of educational videos. Our dataset contains aligned slides and spoken language, for 180+ hours of video and 9000+ slides, with 10 lecturers from various subjects (e.g., computer science, dentistry, biology). We introduce three research tasks, (1) figure-to-text retrieval, (2) text-to-figure retrieval, and (3) generation of slide explanations, which are grounded in multimedia learning and psychology principles to test a vision-language model’s understanding of multimodal content. We provide manual annotations to help implement these tasks and establish baselines on them. Comparing baselines and human student performances, we find that state-of-the-art vision-language models (zero-shot and fine-tuned) struggle in (1) weak crossmodal alignment between slides and spoken text, (2) learning novel visual mediums, (3) technical language, and (4) long-range sequences. We introduce PolyViLT, a novel multimodal transformer trained with a multi-instance learning loss that is more effective than current approaches for retrieval. We conclude by shedding light on the challenges and opportunities in multimodal understanding of educational presentation videos.

Abstract Gestures that accompany speech are an essential part of natural and efficient embodied human communication. The automatic generation of such co‐speech gestures is a long‐standing problem in computer animation and is considered an enabling technology for creating believable characters in film, games, and virtual social spaces, as well as for interaction with social robots. The problem is made challenging by the idiosyncratic and non‐periodic nature of human co‐speech gesture motion, and by the great diversity of communicative functions that gestures encompass. The field of gesture generation has seen surging interest in the last few years, owing to the emergence of more and larger datasets of human gesture motion, combined with strides in deep‐learning‐based generative models that benefit from the growing availability of data. This review article summarizes co‐speech gesture generation research, with a particular focus on deep generative models. First, we articulate the theory describing human gesticulation and how it complements speech. Next, we briefly discuss rule‐based and classical statistical gesture synthesis, before delving into deep learning approaches. We employ the choice of input modalities as an organizing principle, examining systems that generate gestures from audio, text and non‐linguistic input. Concurrent with the exposition of deep learning approaches, we chronicle the evolution of the related training data sets in terms of size, diversity, motion quality, and collection method (e.g., optical motion capture or pose estimation from video). Finally, we identify key research challenges in gesture generation, including data availability and quality; producing human‐like motion; grounding the gesture in the co‐occurring speech in interaction with other speakers, and in the environment; performing gesture evaluation; and integration of gesture synthesis into applications. We highlight recent approaches to tackling the various key challenges, as well as the limitations of these approaches, and point toward areas of future development.

Personalizing an avatar for co-speech gesture generation from spoken language requires learning the idiosyncrasies of a person's gesture style from a small amount of data. Previous methods in gesture generation require large amounts of data for each speaker, which is often infeasible. We propose an approach, named DiffGAN, that efficiently personalizes co-speech gesture generation models of a high-resource source speaker to target speaker with just 2 minutes of target training data. A unique characteristic of DiffGAN is its ability to account for the crossmodal grounding shift, while also addressing the distribution shift in the output domain. We substantiate the effectiveness of our approach a large scale publicly available dataset through quantitative, qualitative and user studies, which show that our proposed methodology significantly outperforms prior approaches for low-resource adaptation of gesture generation. Code and videos can be found at https://chahuja.com/diffgan.

To realize natural-looking virtual agents, one key technical challenge is to automatically generate nonverbal behaviors from spoken language. Since nonverbal behavior varies depending on personality, it is important to generate these nonverbal behaviors to match the expected personality of a virtual agent. In this work, we study how personality traits relate to the process of generating individual nonverbal behaviors from the whole body, including the head, eye gaze, arms, and posture. To study this, we first created a dialogue corpus including transcripts, a broad range of labelled nonverbal behaviors, and the Big Five personality scores of participants in dyad interactions. We constructed models that can predict each nonverbal behavior label given as an input language representation from the participants' spoken sentences. Our experimental results show that personality can help improve the prediction of nonverbal behaviors.

Generating animations from natural language sentences finds its applications in a a number of domains such as movie script visualization, virtual human animation and, robot motion planning. These sentences can describe different kinds of actions, speeds and direction of these actions, and possibly a target destination. The core modeling challenge in this language-to-pose application is how to map linguistic concepts to motion animations. In this paper, we address this multimodal problem by introducing a neural architecture called Joint Language-to-Pose (or JL2P), which learns a joint embedding of language and pose. This joint embedding space is learned end-to-end using a curriculum learning approach which emphasizes shorter and easier sequences first before moving to longer and harder ones. We evaluate our proposed model on a publicly available corpus of 3D pose data and human-annotated sentences. Both objective metrics and human judgment evaluation confirm that our proposed approach is able to generate more accurate animations and are deemed visually more representative by humans than other data driven approaches.

This research aims to create a data-driven end-to-end model for multimodal forecasting body pose and gestures of virtual avatars. A novel aspect of this research is to coalesce both narrative and dialogue for pose forecasting. In a narrative, language is used in a third person view to describe the avatar actions. In dialogue both first and second person views need to be integrated to accurately forecast avatar pose. Gestures and poses of a speaker are linked to other modalities: language and acoustics. We use these correlations to better predict the avatar’s pose.

Non verbal behaviours such as gestures, facial expressions, body posture, and para-linguistic cues have been shown to complement or clarify verbal messages. Hence to improve telepresence, in form of an avatar, it is important to model these behaviours, especially in dyadic interactions. Creating such personalized avatars not only requires to model intrapersonal dynamics between a avatar’s speech and their body pose, but it also needs to model interpersonal dynamics with the interlocutor present in the conversation. In this paper, we introduce a neural architecture named Dyadic Residual-Attention Model (DRAM), which integrates intrapersonal (monadic) and interpersonal (dyadic) dynamics using selective attention to generate sequences of body pose conditioned on audio and body pose of the interlocutor and audio of the human operating the avatar. We evaluate our proposed model on dyadic conversational data consisting of pose and audio of both participants, confirming the importance of adaptive attention between monadic and dyadic dynamics when predicting avatar pose. We also conduct a user study to analyze judgments of human observers. Our results confirm that the generated body pose is more natural, models intrapersonal dynamics and interpersonal dynamics better than non-adaptive monadic/dyadic models.

Our experience of the world is multimodal - we see objects, hear sounds, feel texture, smell odors, and taste flavors. Modality refers to the way in which something happens or is experienced and a research problem is characterized as multimodal when it includes multiple such modalities. In order for Artificial Intelligence to make progress in understanding the world around us, it needs to be able to interpret such multimodal signals together. Multimodal machine learning aims to build models that can process and relate information from multiple modalities. It is a vibrant multi-disciplinary field of increasing importance and with extraordinary potential. Instead of focusing on specific multimodal applications, this paper surveys the recent advances in multimodal machine learning itself and presents them in a common taxonomy. We go beyond the typical early and late fusion categorization and identify broader challenges that are faced by multimodal machine learning, namely: representation, translation, alignment, fusion, and co-learning. This new taxonomy will enable researchers to better understand the state of the field and identify directions for future research.

Recurrent neural networks have shown remarkable success in modeling sequences. However low resource situations still adversely affect the generalizability of these models. We introduce a new family of models, called Lattice Recurrent Units (LRU), to address the challenge of learning deep multi-layer recurrent models with limited resources. LRU models achieve this goal by creating distinct (but coupled) flow of information inside the units: a first flow along time dimension and a second flow along depth dimension. It also offers a symmetry in how information can flow horizontally and vertically. We analyze the effects of decoupling three different components of our LRU model: Reset Gate, Update Gate and Projected State. We evaluate this family of new LRU models on computational convergence rates and statistical efficiency.Our experiments are performed on four publicly-available datasets, comparing with Grid-LSTM and Recurrent Highway networks. Our results show that LRU has better empirical computational convergence rates and statistical efficiency values, along with learning more accurate language models.

Developing individualized head related transfer functions (HRTF) is an essential requirement for accurate virtualization of sound. However it is time consuming and complicated for both the subject and the developer. Obtaining the spectral notches which are the most prominent features of HRTF is very important to reconstruct the head related impulse response (HRIR) accurately. In this paper, a method suitable for fast computation of the frequencies of spectral notches is proposed. The linear prediction residual cepstrum is used to compute the spectral notches with a high degree of accuracy in this work. Subsequent use of Batteaus Reflection model to overlay the spectral notches on the pinna images indicate that the proposed method is able to provide finer contours. Experiments on reconstruction of the HRIR indicates that the method performs better than other methods.