Apoorva Beedu

Apoorva Beedu, Huda Alamri, Irfan Essa

We introduce a Transformer based 6D Object Pose Estimation framework VideoPose, comprising an end-to-end attention based modelling architecture, that attends to previous frames in order to estimate accurate 6D Object Poses in videos. Our approach leverages the temporal information from a video sequence for pose refinement, along with being computationally efficient and robust. Compared to existing methods, our architecture is able to capture and reason from long-range dependencies efficiently, thus iteratively refining over video sequences. Experimental evaluation on the YCB-Video dataset shows that our approach is on par with the state-of-the-art Transformer methods, and performs significantly better relative to CNN based approaches. Further, with a speed of 33 fps, it is also more efficient and therefore applicable to a variety of applications that require real-time object pose estimation. Training code and pretrained models are available at https://github.com/ApoorvaBeedu/VideoPose

Harish Haresamudram, Apoorva Beedu, Mashfiqui Rabbi et al.

Cross-modal contrastive pre-training between natural language and other modalities, e.g., vision and audio, has demonstrated astonishing performance and effectiveness across a diverse variety of tasks and domains. In this paper, we investigate whether such natural language supervision can be used for wearable sensor based Human Activity Recognition (HAR), and discover that-surprisingly-it performs substantially worse than standard end-to-end training and self-supervision. We identify the primary causes for this as: sensor heterogeneity and the lack of rich, diverse text descriptions of activities. To mitigate their impact, we also develop strategies and assess their effectiveness through an extensive experimental evaluation. These strategies lead to significant increases in activity recognition, bringing performance closer to supervised and self-supervised training, while also enabling the recognition of unseen activities and cross modal retrieval of videos. Overall, our work paves the way for better sensor-language learning, ultimately leading to the development of foundational models for HAR using wearables.

Hyeongju Choi, Apoorva Beedu, Harish Haresamudram et al.

To properly assist humans in their needs, human activity recognition (HAR) systems need the ability to fuse information from multiple modalities. Our hypothesis is that multimodal sensors, visual and non-visual tend to provide complementary information, addressing the limitations of other modalities. In this work, we propose a multi-modal framework that learns to effectively combine features from RGB Video and IMU sensors, and show its robustness for MMAct and UTD-MHAD datasets. Our model is trained in two-stage, where in the first stage, each input encoder learns to effectively extract features, and in the second stage, learns to combine these individual features. We show significant improvements of 22% and 11% compared to video only and IMU only setup on UTD-MHAD dataset, and 20% and 12% on MMAct datasets. Through extensive experimentation, we show the robustness of our model on zero shot setting, and limited annotated data setting. We further compare with state-of-the-art methods that use more input modalities and show that our method outperforms significantly on the more difficult MMact dataset, and performs comparably in UTD-MHAD dataset.

Zhikang Dong, Apoorva Beedu, Jason Sheinkopf et al.

Video Language Models (VLMs) are crucial for generalizing across diverse tasks and using language cues to enhance learning. While transformer-based architectures have been the de facto in vision-language training, they face challenges like quadratic computational complexity, high GPU memory usage, and difficulty with long-term dependencies. To address these limitations, we introduce MambaVL, a novel model that leverages recent advancements in selective state space modality fusion to efficiently capture long-range dependencies and learn joint representations for vision and language data. MambaVL utilizes a shared state transition matrix across both modalities, allowing the model to capture information about actions from multiple perspectives within the scene. Furthermore, we propose a question-answering task that helps guide the model toward relevant cues. These questions provide critical information about actions, objects, and environmental context, leading to enhanced performance. As a result, MambaVL achieves state-of-the-art performance in action recognition on the Epic-Kitchens-100 dataset and outperforms baseline methods in action anticipation.

Huda Alamri, Anthony Bilic, Michael Hu et al.

Video-based dialog task is a challenging multimodal learning task that has received increasing attention over the past few years with state-of-the-art obtaining new performance records. This progress is largely powered by the adaptation of the more powerful transformer-based language encoders. Despite this progress, existing approaches do not effectively utilize visual features to help solve tasks. Recent studies show that state-of-the-art models are biased toward textual information rather than visual cues. In order to better leverage the available visual information, this study proposes a new framework that combines 3D-CNN network and transformer-based networks into a single visual encoder to extract more robust semantic representations from videos. The visual encoder is jointly trained end-to-end with other input modalities such as text and audio. Experiments on the AVSD task show significant improvement over baselines in both generative and retrieval tasks.

Ramit Pahwa, Apoorva Beedu, Parivesh Priye et al.

Voice assistants increasingly rely on Speech Language Models (SpeechLMs) to interpret spoken queries and execute complex tasks, yet existing benchmarks lack domain breadth, acoustic diversity, and compositional reasoning complexity to evaluate tool-calling performance. We introduce Audio2Tool, a large-scale dataset comprising approximately 30,000 queries designed to assess tool-calling capabilities of SpeechLMs across three primary domains: Smart Car, Smart Home, and Wearables. Our benchmark features a multi-tier complexity hierarchy, ranging from simple direct commands to complex multi-intent and needle-in-a-haystack extraction to isolate distinct failure modes. To ensure realism, we employ zero-shot voice cloning text-to-speech synthesis and diverse noise profiles to simulate in-the-wild conditions. Evaluations of state-of-the-art SpeechLMs and ASR-LLM pipelines show strong performance on simple commands but significant degradation under compositional and acoustic challenges. We will release the dataset and benchmark upon acceptance.

Apoorva Beedu, Harish Haresamudram, Karan Samel et al.

Anticipating future actions is a highly challenging task due to the diversity and scale of potential future actions; yet, information from different modalities help narrow down plausible action choices. Each modality can provide diverse and often complementary context for the model to learn from. While previous multi-modal methods leverage information from modalities such as video and audio, we primarily explore how text descriptions of actions and objects can also lead to more accurate action anticipation by providing additional contextual cues, e.g., about the environment and its contents. We propose a Multi-modal Contrastive Anticipative Transformer (M-CAT), a video transformer architecture that jointly learns from multi-modal features and text descriptions of actions and objects. We train our model in two stages, where the model first learns to align video clips with descriptions of future actions, and is subsequently fine-tuned to predict future actions. Compared to existing methods, M-CAT has the advantage of learning additional context from two types of text inputs: rich descriptions of future actions during pre-training, and, text descriptions for detected objects and actions during modality feature fusion. Through extensive experimental evaluation, we demonstrate that our model outperforms previous methods on the EpicKitchens datasets, and show that using simple text descriptions of actions and objects aid in more effective action anticipation. In addition, we examine the impact of object and action information obtained via text, and perform extensive ablations.

Apoorva Beedu, Irfan Essa

Video summarization creates an abridged version (i.e., a summary) that provides a quick overview of the video while retaining pertinent information. In this work, we focus on summarizing instructional videos and propose a method for breaking down a video into meaningful segments, each corresponding to essential steps in the video. We propose \textbf{HierSum}, a hierarchical approach that integrates fine-grained local cues from subtitles with global contextual information provided by video-level instructions. Our approach utilizes the ``most replayed" statistic as a supervisory signal to identify critical segments, thereby improving the effectiveness of the summary. We evaluate on benchmark datasets such as TVSum, BLiSS, Mr.HiSum, and the WikiHow test set, and show that HierSum consistently outperforms existing methods in key metrics such as F1-score and rank correlation. We also curate a new multi-modal dataset using WikiHow and EHow videos and associated articles containing step-by-step instructions. Through extensive ablation studies, we demonstrate that training on this dataset significantly enhances summarization on the target datasets.

Hyeongju Choi, Apoorva Beedu, Irfan Essa

Human Activity Recognition (HAR) systems have been extensively studied by the vision and ubiquitous computing communities due to their practical applications in daily life, such as smart homes, surveillance, and health monitoring. Typically, this process is supervised in nature and the development of such systems requires access to large quantities of annotated data. However, the higher costs and challenges associated with obtaining good quality annotations have rendered the application of self-supervised methods an attractive option and contrastive learning comprises one such method. However, a major component of successful contrastive learning is the selection of good positive and negative samples. Although positive samples are directly obtainable, sampling good negative samples remain a challenge. As human activities can be recorded by several modalities like camera and IMU sensors, we propose a hard negative sampling method for multimodal HAR with a hard negative sampling loss for skeleton and IMU data pairs. We exploit hard negatives that have different labels from the anchor but are projected nearby in the latent space using an adjustable concentration parameter. Through extensive experiments on two benchmark datasets: UTD-MHAD and MMAct, we demonstrate the robustness of our approach forlearning strong feature representation for HAR tasks, and on the limited data setting. We further show that our model outperforms all other state-of-the-art methods for UTD-MHAD dataset, and self-supervised methods for MMAct: Cross session, even when uni-modal data are used during downstream activity recognition.

Apoorva Beedu, Zhile Ren, Varun Agrawal et al.

We introduce a simple yet effective algorithm that uses convolutional neural networks to directly estimate object poses from videos. Our approach leverages the temporal information from a video sequence, and is computationally efficient and robust to support robotic and AR domains. Our proposed network takes a pre-trained 2D object detector as input, and aggregates visual features through a recurrent neural network to make predictions at each frame. Experimental evaluation on the YCB-Video dataset show that our approach is on par with the state-of-the-art algorithms. Further, with a speed of 30 fps, it is also more efficient than the state-of-the-art, and therefore applicable to a variety of applications that require real-time object pose estimation.