Search for: All records

We introduce VOCALExplore, a system designed to support users in building domain-specific models over video datasets. VOCALExplore supports interactive labeling sessions and trains models using user-supplied labels. VOCALExplore maximizes model quality by automatically deciding how to select samples based on observed skew in the collected labels. It also selects the optimal video representations to use when training models by casting feature selection as a rising bandit problem. Finally, VOCALExplore implements optimizations to achieve low latency without sacrificing model performance. We demonstrate that VOCALExplore achieves close to the best possible model quality given candidate acquisition functions and feature extractors, and it does so with low visible latency (~1 second per iteration) and no expensive preprocessing. 

We introduce EQUI-VOCAL: a new system that automatically synthesizes queries over videos from limited user interactions. The user only provides a handful of positive and negative examples of what they are looking for. EQUI-VOCAL utilizes these initial examples and additional ones collected through active learning to efficiently synthesize complex user queries. Our approach enables users to find events without database expertise, with limited labeling effort, and without declarative specifications or sketches. Core to EQUI-VOCAL's design is the use of spatio-temporal scene graphs in its data model and query language and a novel query synthesis approach that works on large and noisy video data. Our system outperforms two baseline systems---in terms of F1 score, synthesis time, and robustness to noise---and can flexibly synthesize complex queries that the baselines do not support. 

We demonstrate EQUI-VOCAL, a system that synthesizes compositional queries over videos from user feedback. EQUI-VOCAL enables users to query a video database for complex events by providing a few positive and negative examples of what they are looking for and labeling a small number of additional system-selected examples. Using those user inputs, EQUI-VOCAL synthesizes declarative queries that can then retrieve additional instances of the desired events. The demonstration makes two contributions: it introduces EQUI-VOCAL’s graphical user interface and enables conference attendees to experiment with EQUI-VOCAL on a variety of queries. Both enable users to gain a better understanding of EQUI-VOCAL’s query synthesis approach and to explore the impact of hyperparameters and label noise on system performance. 

ABSTRACT AimThe consistency of patterns in ontogenetic differences in plant traits across the globe has not been thoroughly studied. Environmental conditions affect leaf functional traits, and these effects can differ between adult trees and saplings due to varying environmental conditions in their aerial and soil environments. Our integrative analysis aims to reveal the global universality of woody plants' ontogeny and explores influencing factors. LocationGlobal. Time PeriodStudies published in 1989–2023. Major Taxa StudiedWoody plants. MethodsWe performed a global meta‐analysis of woody plants with different plant functional types at 64 sites around the world, assessed the ontogenetic differences in nine key leaf traits and explored the environmental factors that affected the ontogenetic differences. ResultsWe observed that (1) leaf traits differed significantly between adult trees and saplings, with environmental factors playing varying roles. Photosynthetic capacity per unit area (A_a) and nitrogen content per unit dry mass (N_m) were lower in saplings than in adults under low solar radiation, but this trend reversed with increased solar radiation. Differences in stomatal density (SD) and stable carbon isotope composition (δ¹³C) between adults and saplings were greatest under low solar radiation; (2) ontogenetic differences in leaf thickness (LT), leaf dry mass per area (LMA) and stomatal conductance (g_s) were greater at lower mean annual temperature (MAT); (3) at high mean annual precipitation (MAP), adults had higher nitrogen content per unit area (N_a), while saplings had higherN_mthan adults; (4) soil conditions were strongly correlated with ontogenetic differences in LT and SD, with soil pH as a key driver of variation inA_a, LT, SD,N_aandN_m. Main ConclusionsOur findings indicate that ontogeny strongly modifies leaf functional traits and that multiple environmental factors influence the magnitude of ontogenetic differences in leaf traits. This underscores the importance of considering ontogeny when predicting trait values across plant developmental stages, modelling vegetation composed of individuals of different ages and forecasting vegetation responses to environmental changes. 

We design, implement, and evaluate DeepEverest, a system for the efficient execution of interpretation by example queries over the activation values of a deep neural network. DeepEverest consists of an efficient indexing technique and a query execution algorithm with various optimizations. We prove that the proposed query execution algorithm is instance optimal. Experiments with our prototype show that DeepEverest, using less than 20% of the storage of full materialization, significantly accelerates individual queries by up to 63X and consistently outperforms other methods on multi-query workloads that simulate DNN interpretation processes.