Michael Sidorov

Shubham Agarwal, Ofek Nourian, Michael Sidorov et al.

Understanding plant root systems is critical for advancing research in soil-plant interactions, nutrient uptake, and overall plant health. However, accurate imaging of roots in subterranean environments remains a persistent challenge due to adverse conditions such as occlusion, varying soil moisture, and inherently low contrast, which limit the effectiveness of conventional vision-based approaches. In this work, we propose a novel underground imaging system that captures multiple overlapping views of plant roots and integrates a deep learning-based Multi-Image Super Resolution (MISR) framework designed to enhance root visibility and detail. To train and evaluate our approach, we construct a synthetic dataset that simulates realistic underground imaging scenarios, incorporating key environmental factors that affect image quality. Our proposed MISR algorithm leverages spatial redundancy across views to reconstruct high-resolution images with improved structural fidelity and visual clarity. Quantitative evaluations show that our approach outperforms state-of-the-art super resolution baselines, achieving a 2.3 percent reduction in BRISQUE, indicating improved image quality with the same CLIP-IQA score, thereby enabling enhanced phenotypic analysis of root systems. This, in turn, facilitates accurate estimation of critical root traits, including root hair count and root hair density. The proposed framework presents a promising direction for robust automatic underground plant root imaging and trait quantification for agricultural and ecological research.

Michael Sidorov, Dan Vilenchik

It's by now folklore that to understand the activity pattern of a user in an online social network (OSN) platform, one needs to look at his friends or the ones he follows. The common perception is that these friends exert influence on the user, effecting his decision whether to re-share content or not. Hinging upon this intuition, a variety of models were developed to predict how information propagates in OSN, similar to the way infection spreads in the population. In this paper, we revisit this world view and arrive at new conclusions. Given a set of users $V$, we study the task of predicting whether a user $u \in V$ will re-share content by some $v \in V$ at the following time window given the activity of all the users in $V$ in the previous time window. We design several algorithms for this task, ranging from a simple greedy algorithm that only learns $u$'s conditional probability distribution, ignoring the rest of $V$, to a convolutional neural network-based algorithm that receives the activity of all of $V$, but does not receive explicitly the social link structure. We tested our algorithms on four datasets that we collected from Twitter, each revolving around a different popular topic in 2020. The best performance, average F1-score of 0.86 over the four datasets, was achieved by the convolutional neural network. The simple, social-link ignorant, algorithm achieved an average F1-score of 0.78.

Shihab Aaqil Ahamed, Malitha Gunawardhana, Liel David et al.

Current video-based Masked Autoencoders (MAEs) primarily focus on learning effective spatiotemporal representations from a visual perspective, which may lead the model to prioritize general spatial-temporal patterns but often overlook nuanced semantic attributes like specific interactions or sequences that define actions - such as action-specific features that align more closely with human cognition for space-time correspondence. This can limit the model's ability to capture the essence of certain actions that are contextually rich and continuous. Humans are capable of mapping visual concepts, object view invariance, and semantic attributes available in static instances to comprehend natural dynamic scenes or videos. Existing MAEs for videos and static images rely on separate datasets for videos and images, which may lack the rich semantic attributes necessary for fully understanding the learned concepts, especially when compared to using video and corresponding sampled frame images together. To this end, we propose CrossVideoMAE an end-to-end self-supervised cross-modal contrastive learning MAE that effectively learns both video-level and frame-level rich spatiotemporal representations and semantic attributes. Our method integrates mutual spatiotemporal information from videos with spatial information from sampled frames within a feature-invariant space, while encouraging invariance to augmentations within the video domain. This objective is achieved through jointly embedding features of visible tokens and combining feature correspondence within and across modalities, which is critical for acquiring rich, label-free guiding signals from both video and frame image modalities in a self-supervised manner. Extensive experiments demonstrate that our approach surpasses previous state-of-the-art methods and ablation studies validate the effectiveness of our approach.

Daniel Harari, Michael Sidorov, Liel David et al.

Large multi-modal models (LMMs) show increasing performance in realistic visual tasks for images and, more recently, for videos. For example, given a video sequence, such models are able to describe in detail objects, the surroundings and dynamic actions. In this study, we explored the extent to which these models ground their semantic understanding in the actual visual input. Specifically, given sequences of hands interacting with objects, we asked models when and where the interaction begins or ends. For this purpose, we introduce a first of its kind, large-scale dataset with more than 20K annotated interactions on videos from the Something-Something-V2 dataset. 250 AMTurk human annotators labeled core interaction events, particularly when and where objects and agents become attached ('contact') or detached ('release'). We asked two LMMs (Qwen-2.5VL and GPT-4o) to locate these events in short videos, each with a single event. The results show that although the models can reliably name the target objects, identify the action and provide coherent reasoning, they consistently fail to identify the frame where the interaction begins or ends and cannot localize the event within the scene. Our findings suggest that in struggling to pinpoint the moment and location of physical contact that defines the interaction, the models lack the perceptual grounding required for deeper understanding of dynamic scenes.