Large models achieve strong performance on Vision-and-Language Navigation (VLN) tasks, but are costly to run in resource-limited environments.Token pruning offers appealing tradeoffs for efficiency with minimal performance loss by reducing model input size, but prior work overlooks VLN-specific challenges.For example, information loss from pruning can effectively increase computational cost due to longer walks.Thus, the inability to identify uninformative tokens undermines the supposed efficiency gains from pruning.To address this, we propose Navigation-Aware Pruning (NAP), which uses navigation-specific traits to simplify the pruning process by pre-filtering tokens into foreground and background.For example, image views are filtered based on whether the agent can navigate in that direction.We also extract navigation-relevant instructions using a Large Language Model.After filtering, we focus pruning on background tokens, minimizing information loss.To further help avoid increases in navigation length, we discourage backtracking by removing low-importance navigation nodes.Experiments on standard VLN benchmarks show NAP significantly outperforms prior work, preserving higher success rates while saving more than 50% FLOPS 1 .

Using the ear as a biometric identifier, particularly for children in healthcare settings, has an important advantage over using the face - the privacy of the person can be protected better. However, aging and the resulting appearance differences, known to be challenges for face recognition models, have not been addressed for ear recognition yet. To address this limitation, we curated a publicly available dataset, which we call Ears of Infant Cohort in Zambia with Aging (EICZA)1. The dataset contains 3,330 ear images of 177 subjects, each photographed multiple times between the ages of 6 days and 9 months, when ear growth is most significant. For the task of age-constrained ear recognition, i.e., recognizing a person who has aged since the model was trained, we propose a new ear recognition model, called SASE for Self-Attention-based Sequential Ear image analysis. The model takes a sequence of ear images at early but different ages as input (instead of a single image) and processes them with a feature extraction network and a Transformer encoder. Trained with a large margin cosine loss function, the model is encouraged to learn a feature representation that distinguishes subjects from each other: Our experiments show that accounting for age enables our model to outperform other models that do not in recognizing ears that have grown and look different in later time periods.

Scene text recognition is the task of recognizing character sequences in images of natural scenes. The considerable diversity in the appearance of text in a scene image and potentially highly complex backgrounds make text recognition challenging. Previous approaches employ character sequence generators to analyze text regions and, subsequently, compare the candidate character sequences against a language model. In this work, we propose a bimodal framework that simultaneously utilizes visual and linguistic information to enhance recognition performance. Our linguistically aware learning (LAL) method effectively learns visual embeddings using a rectifier, encoder, and attention decoder approach, and linguistic embeddings, using a deep next-character prediction model. We present an innovative way of combining these two embeddings effectively. Our experiments on eight standard benchmarks show that our method outperforms previous methods by large margins, particularly on rotated, foreshortened, and curved text. We show that the bimodal approach has a statistically significant impact. We also contribute a new dataset, and show robust performance when LAL is combined with a text detector in a pipelined text spotting framework.

The emerging technologies for connected vehicles have become hot topics. In addition, connected vehicle applications are generally found in heterogeneous wireless networks. In such a context, user terminals face the challenge of access network selection. The method of selecting the appropriate access network is quite important for connected vehicle applications. This paper jointly considers multiple decision factors to facilitate vehicle-to-infrastructure networking, where the energy efficiency of the networks is adopted as an important factor in the network selection process. To effectively characterize users' preference and network performance, we exploit energy efficiency, signal intensity, network cost, delay, and bandwidth to establish utility functions. Then, these utility functions and multi-criteria utility theory are used to construct an energy-efficient network selection approach. We propose design strategies to establish a joint multi-criteria utility function for network selection. Then, we model network selection in connected vehicle applications as a multi-constraint optimization problem. Finally, a multi-criteria access selection algorithm is presented to solve the built model. Simulation results show that the proposed access network selection approach is feasible and effective.