Search

With the growing demand for solutions to real-world video challenges, interest in dense video captioning (DVC) has been on the rise. DVC involves the automatic captioning and localization of untrimmed videos. Several studies highlight the challenges of DVC and introduce improved methods utilizing prior knowledge, such as pre-training and external memory. In this research, we propose a model that leverages the prior knowledge of human-oriented hierarchical compact memory inspired by human memory hierarchy and cognition. To mimic human-like memory recall, we construct a hierarchical memory and a hierarchical memory reading module. We build an efficient hierarchical compact memory by employing clustering of memory events and summarization using large language models. Comparative experiments demonstrate that this hierarchical memory recall process improves the performance of DVC by achieving state-of-the-art performance on YouCook2 and ViTT datasets., Comment: AAAI2025

Visual Question Answering with Natural Language Explanation (VQA-NLE) task is challenging due to its high demand for reasoning-based inference. Recent VQA-NLE studies focus on enhancing model networks to amplify the model's reasoning capability but this approach is resource-consuming and unstable. In this work, we introduce a new VQA-NLE model, ReRe (Retrieval-augmented natural language Reasoning), using leverage retrieval information from the memory to aid in generating accurate answers and persuasive explanations without relying on complex networks and extra datasets. ReRe is an encoder-decoder architecture model using a pre-trained clip vision encoder and a pre-trained GPT-2 language model as a decoder. Cross-attention layers are added in the GPT-2 for processing retrieval features. ReRe outperforms previous methods in VQA accuracy and explanation score and shows improvement in NLE with more persuasive, reliability., Comment: ICIP Workshop 2024

The investigation of emerging non-toxic perovskite materials has been undertaken to advance the fabrication of environmentally sustainable lead-free perovskite solar cells. This study introduces a machine learning methodology aimed at predicting innovative halide perovskite materials that hold promise for use in photovoltaic applications. The seven newly predicted materials are as follows: CsMnCl$_4$, Rb$_3$Mn$_2$Cl$_9$, Rb$_4$MnCl$_6$, Rb$_3$MnCl$_5$, RbMn$_2$Cl$_7$, RbMn$_4$Cl$_9$, and CsIn$_2$Cl$_7$. The predicted compounds are first screened using a machine learning approach, and their validity is subsequently verified through density functional theory calculations. CsMnCl$_4$ is notable among them, displaying a bandgap of 1.37 eV, falling within the Shockley-Queisser limit, making it suitable for photovoltaic applications. Through the integration of machine learning and density functional theory, this study presents a methodology that is more effective and thorough for the discovery and design of materials.

Recent advancements in deep neural networks have shown promise in aiding disease diagnosis and medical decision-making. However, ensuring transparent decision-making processes of AI models in compliance with regulations requires a comprehensive understanding of the model's internal workings. However, previous methods heavily rely on expensive pixel-wise annotated datasets for interpreting the model, presenting a significant drawback in medical domains. In this paper, we propose a novel medical neuron concept annotation method, named Mask-free Medical Model Interpretation (MAMMI), addresses these challenges. By using a vision-language model, our method relaxes the need for pixel-level masks for neuron concept annotation. MAMMI achieves superior performance compared to other interpretation methods, demonstrating its efficacy in providing rich representations for neurons in medical image analysis. Our experiments on a model trained on NIH chest X-rays validate the effectiveness of MAMMI, showcasing its potential for transparent clinical decision-making in the medical domain. The code is available at https://github.com/ailab-kyunghee/MAMMI., Comment: MICCAI 2024

There has been significant attention to the research on dense video captioning, which aims to automatically localize and caption all events within untrimmed video. Several studies introduce methods by designing dense video captioning as a multitasking problem of event localization and event captioning to consider inter-task relations. However, addressing both tasks using only visual input is challenging due to the lack of semantic content. In this study, we address this by proposing a novel framework inspired by the cognitive information processing of humans. Our model utilizes external memory to incorporate prior knowledge. The memory retrieval method is proposed with cross-modal video-to-text matching. To effectively incorporate retrieved text features, the versatile encoder and the decoder with visual and textual cross-attention modules are designed. Comparative experiments have been conducted to show the effectiveness of the proposed method on ActivityNet Captions and YouCook2 datasets. Experimental results show promising performance of our model without extensive pretraining from a large video dataset., Comment: CVPR 2024

This study demonstrates the developments of self-assembled optical metasurfaces to overcome inherent limitations in polarization density (P) within natural materials, which hinder achieving high refractive indices (n) at optical frequencies. The Maxwellian macroscopic description establishes a link between P and n, revealing a static limit in natural materials, restricting n to approximately 4.0 at optical frequencies. Optical metasurfaces, utilizing metallic colloids on a deep-subwavelength scale, offer a solution by unnaturally enhancing n through electric dipolar (ED) resonances. Self-assembly enables the creation of nanometer-scale metallic gaps between metallic nanoparticles (NPs), paving the way for achieving exceptionally high n at optical frequencies. This study focuses on assembling polyhedral gold (Au) NPs into a closely packed monolayer by rationally designing the polymeric ligand to balance attractive and repulsive forces, in that polymeric brush-mediated self-assembly of the close-packed Au NP monolayer is robustly achieved over a large-area. The resulting monolayer of Au nanospheres (NSs), nanooctahedras (NOs), and nanocubes (NCs) exhibits high macroscopic integrity and crystallinity, sufficiently enough for pushing n to record-high regimes. The study underlies the significance of capacitive coupling in achieving an unnaturally high n and explores fine-tuning Au NC size to optimize this coupling. The achieved n of 10.12 at optical frequencies stands as a benchmark, highlighting the potential of polyhedral Au NPs in advancing optical metasurfaces.

Recent advancements in neural networks have showcased their remarkable capabilities across various domains. Despite these successes, the "black box" problem still remains. Addressing this, we propose a novel framework, WWW, that offers the 'what', 'where', and 'why' of the neural network decisions in human-understandable terms. Specifically, WWW utilizes adaptive selection for concept discovery, employing adaptive cosine similarity and thresholding techniques to effectively explain 'what'. To address the 'where' and 'why', we proposed a novel combination of neuron activation maps (NAMs) with Shapley values, generating localized concept maps and heatmaps for individual inputs. Furthermore, WWW introduces a method for predicting uncertainty, leveraging heatmap similarities to estimate 'how' reliable the prediction is. Experimental evaluations of WWW demonstrate superior performance in both quantitative and qualitative metrics, outperforming existing methods in interpretability. WWW provides a unified solution for explaining 'what', 'where', and 'why', introducing a method for localized explanations from global interpretations and offering a plug-and-play solution adaptable to various architectures., Comment: CVPR 2024

We construct an emergent holographic dual description in the Luttinger-Ward functional approach, where the renormalization group (RG) flows of collective bi-local fields appear manifestly in the bulk effective action with an emergent extra dimension. This holographic dual effective field theory reproduces $1/N$ quantum corrections in a self-consistent manner when we take the UV limit in the bulk effective action. Going into the IR regime in the extra dimension, we observe that a partial class of the field theoretic $1/N$, $1/N^{2}$, ... quantum corrections are resummed in the all-loop order and reorganized to form a holographic dual effective field theory in a large $N$ fashion living on the one-higher dimensional spacetime. In this study, we apply this theoretical framework into an Sachdev-Ye-Kitaev (SYK) model. Taking the large $N$ limit in the holographic dual effective field theory, we obtain nonlinearly coupled second-order bulk differential equations of motion for the three bi-local order-parameter fields of fermion self-energy, Green's function, and polarization function. Here, both UV and IR boundary conditions are derived self-consistently from the boundary effective action. We solve these highly intertwined nonlinear differential equations based on the so called matching method. Our ansatz for the bi-local order-parameter fields coincide with the conformally invariant solution of the field theoretic large $N$ limit in the UV limit, but their overall coefficients $RG-flow$ along the extra dimensional space, respectively, reflecting effects of higher-order quantum corrections. As a result, we find an insulating behavior, where the self-energy diverges at IR. ..., Comment: Regularizations have been clarified and a general scope has been discussed