Harpreet Sawhney

Anshul Shah, Benjamin Lundell, Harpreet Sawhney et al.

We address the problem of extracting key steps from unlabeled procedural videos, motivated by the potential of Augmented Reality (AR) headsets to revolutionize job training and performance. We decompose the problem into two steps: representation learning and key steps extraction. We propose a training objective, Bootstrapped Multi-Cue Contrastive (BMC2) loss to learn discriminative representations for various steps without any labels. Different from prior works, we develop techniques to train a light-weight temporal module which uses off-the-shelf features for self supervision. Our approach can seamlessly leverage information from multiple cues like optical flow, depth or gaze to learn discriminative features for key-steps, making it amenable for AR applications. We finally extract key steps via a tunable algorithm that clusters the representations and samples. We show significant improvements over prior works for the task of key step localization and phase classification. Qualitative results demonstrate that the extracted key steps are meaningful and succinctly represent various steps of the procedural tasks.

Ashraful Islam, Ben Lundell, Harpreet Sawhney et al.

We present a self-supervised learning (SSL) method suitable for semi-global tasks such as object detection and semantic segmentation. We enforce local consistency between self-learned features, representing corresponding image locations of transformed versions of the same image, by minimizing a pixel-level local contrastive (LC) loss during training. LC-loss can be added to existing self-supervised learning methods with minimal overhead. We evaluate our SSL approach on two downstream tasks -- object detection and semantic segmentation, using COCO, PASCAL VOC, and CityScapes datasets. Our method outperforms the existing state-of-the-art SSL approaches by 1.9% on COCO object detection, 1.4% on PASCAL VOC detection, and 0.6% on CityScapes segmentation.

Lijun Zhang, Nikhil Chacko, Petter Nilsson et al.

Automated warehouses execute millions of stow operations, where robots place objects into storage bins. For these systems it is valuable to anticipate how a bin will look from the current observations and the planned stow behavior before real execution. We propose FOREST, a stow-intent-conditioned world model that represents bin states as item-aligned instance masks and uses a latent diffusion transformer to predict the post-stow configuration from the observed context. Our evaluation shows that FOREST substantially improves the geometric agreement between predicted and true post-stow layouts compared with heuristic baselines. We further evaluate the predicted post-stow layouts in two downstream tasks, in which replacing the real post-stow masks with FOREST predictions causes only modest performance loss in load-quality assessment and multi-stow reasoning, indicating that our model can provide useful foresight signals for warehouse planning.

Aditya Prakash, Benjamin Lundell, Dmitry Andreychuk et al.

We tackle the novel problem of predicting 3D hand motion and contact maps (or Interaction Trajectories) given a single RGB view, action text, and a 3D contact point on the object as input. Our approach consists of (1) Interaction Codebook: a VQVAE model to learn a latent codebook of hand poses and contact points, effectively tokenizing interaction trajectories, (2) Interaction Predictor: a transformer-decoder module to predict the interaction trajectory from test time inputs by using an indexer module to retrieve a latent affordance from the learned codebook. To train our model, we develop a data engine that extracts 3D hand poses and contact trajectories from the diverse HoloAssist dataset. We evaluate our model on a benchmark that is 2.5-10X larger than existing works, in terms of diversity of objects and interactions observed, and test for generalization of the model across object categories, action categories, tasks, and scenes. Experimental results show the effectiveness of our approach over transformer & diffusion baselines across all settings.

Yiye Chen, Harpreet Sawhney, Nicholas Gydé et al.

Scene graphs have emerged as a structured and serializable environment representation for grounded spatial reasoning with Large Language Models (LLMs). In this work, we propose SG^2, an iterative Schema-Guided Scene-Graph reasoning framework based on multi-agent LLMs. The agents are grouped into two modules: a (1) Reasoner module for abstract task planning and graph information queries generation, and a (2) Retriever module for extracting corresponding graph information based on code-writing following the queries. Two modules collaborate iteratively, enabling sequential reasoning and adaptive attention to graph information. The scene graph schema, prompted to both modules, serves to not only streamline both reasoning and retrieval process, but also guide the cooperation between two modules. This eliminates the need to prompt LLMs with full graph data, reducing the chance of hallucination due to irrelevant information. Through experiments in multiple simulation environments, we show that our framework surpasses existing LLM-based approaches and baseline single-agent, tool-based Reason-while-Retrieve strategy in numerical Q\&A and planning tasks.

Huseyin Coskun, Zeeshan Zia, Bugra Tekin et al.

The lack of large-scale real datasets with annotations makes transfer learning a necessity for video activity understanding. We aim to develop an effective method for few-shot transfer learning for first-person action classification. We leverage independently trained local visual cues to learn representations that can be transferred from a source domain, which provides primitive action labels, to a different target domain using only a handful of examples. Visual cues we employ include object-object interactions, hand grasps and motion within regions that are a function of hand locations. We employ a framework based on meta-learning to extract the distinctive and domain invariant components of the deployed visual cues. This enables transfer of action classification models across public datasets captured with diverse scene and action configurations. We present comparative results of our transfer learning methodology and report superior results over state-of-the-art action classification approaches for both inter-class and inter-dataset transfer.

Mohamed Elhoseiny, Jingen Liu, Hui Cheng et al.

We propose a new zero-shot Event Detection method by Multi-modal Distributional Semantic embedding of videos. Our model embeds object and action concepts as well as other available modalities from videos into a distributional semantic space. To our knowledge, this is the first Zero-Shot event detection model that is built on top of distributional semantics and extends it in the following directions: (a) semantic embedding of multimodal information in videos (with focus on the visual modalities), (b) automatically determining relevance of concepts/attributes to a free text query, which could be useful for other applications, and (c) retrieving videos by free text event query (e.g., "changing a vehicle tire") based on their content. We embed videos into a distributional semantic space and then measure the similarity between videos and the event query in a free text form. We validated our method on the large TRECVID MED (Multimedia Event Detection) challenge. Using only the event title as a query, our method outperformed the state-of-the-art that uses big descriptions from 12.6% to 13.5% with MAP metric and 0.73 to 0.83 with ROC-AUC metric. It is also an order of magnitude faster.

S. Hussain Raza, Omar Javed, Aveek Das et al.

We present an algorithm to estimate depth in dynamic video scenes. We propose to learn and infer depth in videos from appearance, motion, occlusion boundaries, and geometric context of the scene. Using our method, depth can be estimated from unconstrained videos with no requirement of camera pose estimation, and with significant background/foreground motions. We start by decomposing a video into spatio-temporal regions. For each spatio-temporal region, we learn the relationship of depth to visual appearance, motion, and geometric classes. Then we infer the depth information of new scenes using piecewise planar parametrization estimated within a Markov random field (MRF) framework by combining appearance to depth learned mappings and occlusion boundary guided smoothness constraints. Subsequently, we perform temporal smoothing to obtain temporally consistent depth maps. To evaluate our depth estimation algorithm, we provide a novel dataset with ground truth depth for outdoor video scenes. We present a thorough evaluation of our algorithm on our new dataset and the publicly available Make3d static image dataset.