TULIP: Token-length Upgraded CLIP

We address the challenge of representing long captions in vision-language models, such as CLIP. By design these models are limited by fixed, absolute positional encodings, restricting inputs to a maximum of 77 tokens and hindering performance on tasks requiring longer descriptions. Although recent work has attempted to overcome this limit, their proposed approaches struggle to model token relationships over longer distances and simply extend to a fixed new token length. Instead, we propose a generalizable method, named TULIP, able to upgrade the token length to any length for CLIP-like models. We do so by improving the architecture with relative position encodings, followed by a training procedure that (i) distills the original CLIP text encoder into an encoder with relative position encodings and (ii) enhances the model for aligning longer captions with images. By effectively encoding captions longer than the default 77 tokens, our model outperforms baselines on cross-modal tasks such as retrieval and text-to-image generation.

Set2Seq Transformer: Learning Permutation Aware Set Representations of Artistic Sequences

We propose Set2Seq Transformer, a novel sequential multiple instance architecture, that learns to rank permutation aware set representations of sequences. First, we illustrate that learning temporal position-aware representations of discrete timesteps can greatly improve static visual multiple instance learning methods that do not regard temporality and concentrate almost exclusively on visual content analysis. We further demonstrate the significant advantages of end-to-end sequential multiple instance learning, integrating visual content and temporal information in a multimodal manner. As application we focus on fine art analysis related tasks. To that end, we show that our Set2Seq Transformer can leverage visual set and temporal position-aware representations for modelling visual artists' oeuvres for predicting artistic success. Finally, through extensive quantitative and qualitative evaluation using a novel dataset, WikiArt-Seq2Rank, and a visual learning-to-rank downstream task, we show that our Set2Seq Transformer captures essential temporal information improving the performance of strong static and sequential multiple instance learning methods for predicting artistic success.

Co-Representation Neural Hypergraph Diffusion for Edge-Dependent Node Classification

Hypergraphs are widely employed to represent complex higher-order relationships in real-world applications. Most hypergraph learning research focuses on node- or edge-level tasks. A practically relevant but more challenging task, edge-dependent node classification (ENC), is only recently proposed. In ENC, a node can have different labels across different hyperedges, which requires the modeling of node-hyperedge pairs instead of single nodes or hyperedges. Existing solutions for this task are based on message passing and model within-edge and within-node interactions as multi-input single-output functions. This brings three limitations: (1) non-adaptive representation size, (2) node/edge agnostic messages, and (3) insufficient interactions among nodes or hyperedges. To tackle these limitations, we develop CoNHD, a new solution based on hypergraph diffusion. Specifically, we first extend hypergraph diffusion using node-hyperedge co-representations. This extension explicitly models both within-edge and within-node interactions as multi-input multi-output functions using two equivariant diffusion operators. To avoid handcrafted regularization functions, we propose a neural implementation for the co-representation hypergraph diffusion process. Extensive experiments demonstrate the effectiveness and efficiency of the proposed CoNHD model.

Ada-HGNN: Adaptive Sampling for Scalable Hypergraph Neural Networks

Hypergraphs serve as an effective model for depicting complex connections in various real-world scenarios, from social to biological networks. The development of Hypergraph Neural Networks (HGNNs) has emerged as a valuable method to manage the intricate associations in data, though scalability is a notable challenge due to memory limitations. In this study, we introduce a new adaptive sampling strategy specifically designed for hypergraphs, which tackles their unique complexities in an efficient manner. We also present a Random Hyperedge Augmentation (RHA) technique and an additional Multilayer Perceptron (MLP) module to improve the robustness and generalization capabilities of our approach. Thorough experiments with real-world datasets have proven the effectiveness of our method, markedly reducing computational and memory demands while maintaining performance levels akin to conventional HGNNs and other baseline models. This research paves the way for improving both the scalability and efficacy of HGNNs in extensive applications. We will also make our codebase publicly accessible.

GO4Align: Group Optimization for Multi-Task Alignment

This paper proposes \textit{GO4Align}, a multi-task optimization approach that tackles task imbalance by explicitly aligning the optimization across tasks. To achieve this, we design an adaptive group risk minimization strategy, compromising two crucial techniques in implementation: (i) dynamical group assignment, which clusters similar tasks based on task interactions; (ii) risk-guided group indicators, which exploit consistent task correlations with risk information from previous iterations. Comprehensive experimental results on diverse typical benchmarks demonstrate our method's performance superiority with even lower computational costs.

Conditional Modeling Based Automatic Video Summarization

The aim of video summarization is to shorten videos automatically while retaining the key information necessary to convey the overall story. Video summarization methods mainly rely on visual factors, such as visual consecutiveness and diversity, which may not be sufficient to fully understand the content of the video. There are other non-visual factors, such as interestingness, representativeness, and storyline consistency that should also be considered for generating high-quality video summaries. Current methods do not adequately take into account these non-visual factors, resulting in suboptimal performance. In this work, a new approach to video summarization is proposed based on insights gained from how humans create ground truth video summaries. The method utilizes a conditional modeling perspective and introduces multiple meaningful random variables and joint distributions to characterize the key components of video summarization. Helper distributions are employed to improve the training of the model. A conditional attention module is designed to mitigate potential performance degradation in the presence of multi-modal input. The proposed video summarization method incorporates the above innovative design choices that aim to narrow the gap between human-generated and machine-generated video summaries. Extensive experiments show that the proposed approach outperforms existing methods and achieves state-of-the-art performance on commonly used video summarization datasets.

Episodic Multi-Task Learning with Heterogeneous Neural Processes

This paper focuses on the data-insufficiency problem in multi-task learning within an episodic training setup. Specifically, we explore the potential of heterogeneous information across tasks and meta-knowledge among episodes to effectively tackle each task with limited data. Existing meta-learning methods often fail to take advantage of crucial heterogeneous information in a single episode, while multi-task learning models neglect reusing experience from earlier episodes. To address the problem of insufficient data, we develop Heterogeneous Neural Processes (HNPs) for the episodic multi-task setup. Within the framework of hierarchical Bayes, HNPs effectively capitalize on prior experiences as meta-knowledge and capture task-relatedness among heterogeneous tasks, mitigating data-insufficiency. Meanwhile, transformer-structured inference modules are designed to enable efficient inferences toward meta-knowledge and task-relatedness. In this way, HNPs can learn more powerful functional priors for adapting to novel heterogeneous tasks in each meta-test episode. Experimental results show the superior performance of the proposed HNPs over typical baselines, and ablation studies verify the effectiveness of the designed inference modules.

Small Visual Language Models can also be Open-Ended Few-Shot Learners

We present Self-Context Adaptation (SeCAt), a self-supervised approach that unlocks open-ended few-shot abilities of small visual language models. Our proposed adaptation algorithm explicitly learns from symbolic, yet self-supervised training tasks. Specifically, our approach imitates image captions in a self-supervised way based on clustering a large pool of images followed by assigning semantically-unrelated names to clusters. By doing so, we construct the `self-context', a training signal consisting of interleaved sequences of image and pseudo-caption pairs and a query image for which the model is trained to produce the right pseudo-caption. We demonstrate the performance and flexibility of SeCAt on several multimodal few-shot datasets, spanning various granularities. By using models with approximately 1B parameters we outperform the few-shot abilities of much larger models, such as Frozen and FROMAGe. SeCAt opens new possibilities for research in open-ended few-shot learning that otherwise requires access to large or proprietary models.

Prototype-Enhanced Hypergraph Learning for Heterogeneous Information Networks

The variety and complexity of relations in multimedia data lead to Heterogeneous Information Networks (HINs). Capturing the semantics from such networks requires approaches capable of utilizing the full richness of the HINs. Existing methods for modeling HINs employ techniques originally designed for graph neural networks, and HINs decomposition analysis, like using manually predefined metapaths. In this paper, we introduce a novel prototype-enhanced hypergraph learning approach for node classification in HINs. Using hypergraphs instead of graphs, our method captures higher-order relationships among nodes and extracts semantic information without relying on metapaths. Our method leverages the power of prototypes to improve the robustness of the hypergraph learning process and creates the potential to provide human-interpretable insights into the underlying network structure. Extensive experiments on three real-world HINs demonstrate the effectiveness of our method.

ProtoExplorer: Interpretable Forensic Analysis of Deepfake Videos using Prototype Exploration and Refinement

In high-stakes settings, Machine Learning models that can provide predictions that are interpretable for humans are crucial. This is even more true with the advent of complex deep learning based models with a huge number of tunable parameters. Recently, prototype-based methods have emerged as a promising approach to make deep learning interpretable. We particularly focus on the analysis of deepfake videos in a forensics context. Although prototype-based methods have been introduced for the detection of deepfake videos, their use in real-world scenarios still presents major challenges, in that prototypes tend to be overly similar and interpretability varies between prototypes. This paper proposes a Visual Analytics process model for prototype learning, and, based on this, presents ProtoExplorer, a Visual Analytics system for the exploration and refinement of prototype-based deepfake detection models. ProtoExplorer offers tools for visualizing and temporally filtering prototype-based predictions when working with video data. It disentangles the complexity of working with spatio-temporal prototypes, facilitating their visualization. It further enables the refinement of models by interactively deleting and replacing prototypes with the aim to achieve more interpretable and less biased predictions while preserving detection accuracy. The system was designed with forensic experts and evaluated in a number of rounds based on both open-ended think aloud evaluation and interviews. These sessions have confirmed the strength of our prototype based exploration of deepfake videos while they provided the feedback needed to continuously improve the system.