Multi-frame infrared small target (MIRST) detection in satellite videos is a long-standing, fundamental yet challenging task for decades, and the challenges can be summarized as: First, extremely small target size, highly complex clutters & noises, various satellite motions result in limited feature representation, high false alarms, and difficult motion analyses. Second, the lack of large-scale public available MIRST dataset in satellite videos greatly hinders the algorithm development. To address the aforementioned challenges, in this paper, we first build a large-scale dataset for MIRST detection in satellite videos (namely IRSatVideo-LEO), and then develop a recurrent feature refinement (RFR) framework as the baseline method. Specifically, IRSatVideo-LEO is a semi-simulated dataset with synthesized satellite motion, target appearance, trajectory and intensity, which can provide a standard toolbox for satellite video generation and a reliable evaluation platform to facilitate the algorithm development. For baseline method, RFR is proposed to be equipped with existing powerful CNN-based methods for long-term temporal dependency exploitation and integrated motion compensation & MIRST detection. Specifically, a pyramid deformable alignment (PDA) module and a temporal-spatial-frequency modulation (TSFM) module are proposed to achieve effective and efficient feature alignment, propagation, aggregation and refinement. Extensive experiments have been conducted to demonstrate the effectiveness and superiority of our scheme. The comparative results show that ResUNet equipped with RFR outperforms the state-of-the-art MIRST detection methods. Dataset and code are released at //github.com/XinyiYing/RFR.
相關內容
Advances in generative models have made it possible for AI-generated text, code, and images to mirror human-generated content in many applications. Watermarking, a technique that aims to embed information in the output of a model to verify its source, is useful for mitigating the misuse of such AI-generated content. However, we show that common design choices in LLM watermarking schemes make the resulting systems surprisingly susceptible to attack -- leading to fundamental trade-offs in robustness, utility, and usability. To navigate these trade-offs, we rigorously study a set of simple yet effective attacks on common watermarking systems, and propose guidelines and defenses for LLM watermarking in practice.
This paper presents SimBase, a simple yet effective baseline for temporal video grounding. While recent advances in temporal grounding have led to impressive performance, they have also driven network architectures toward greater complexity, with a range of methods to (1) capture temporal relationships and (2) achieve effective multimodal fusion. In contrast, this paper explores the question: How effective can a simplified approach be? To investigate, we design SimBase, a network that leverages lightweight, one-dimensional temporal convolutional layers instead of complex temporal structures. For cross-modal interaction, SimBase only employs an element-wise product instead of intricate multimodal fusion. Remarkably, SimBase achieves state-of-the-art results on two large-scale datasets. As a simple yet powerful baseline, we hope SimBase will spark new ideas and streamline future evaluations in temporal video grounding.
Spatio-temporal coherency is a major challenge in synthesizing high quality videos, particularly in synthesizing human videos that contain rich global and local deformations. To resolve this challenge, previous approaches have resorted to different features in the generation process aimed at representing appearance and motion. However, in the absence of strict mechanisms to guarantee such disentanglement, a separation of motion from appearance has remained challenging, resulting in spatial distortions and temporal jittering that break the spatio-temporal coherency. Motivated by this, we here propose LEO, a novel framework for human video synthesis, placing emphasis on spatio-temporal coherency. Our key idea is to represent motion as a sequence of flow maps in the generation process, which inherently isolate motion from appearance. We implement this idea via a flow-based image animator and a Latent Motion Diffusion Model (LMDM). The former bridges a space of motion codes with the space of flow maps, and synthesizes video frames in a warp-and-inpaint manner. LMDM learns to capture motion prior in the training data by synthesizing sequences of motion codes. Extensive quantitative and qualitative analysis suggests that LEO significantly improves coherent synthesis of human videos over previous methods on the datasets TaichiHD, FaceForensics and CelebV-HQ. In addition, the effective disentanglement of appearance and motion in LEO allows for two additional tasks, namely infinite-length human video synthesis, as well as content-preserving video editing.
Harmonizing Pixels and Melodies: Maestro-Guided Film Score Generation and Composition Style Transfer
We introduce a film score generation framework to harmonize visual pixels and music melodies utilizing a latent diffusion model. Our framework processes film clips as input and generates music that aligns with a general theme while offering the capability to tailor outputs to a specific composition style. Our model directly produces music from video, utilizing a streamlined and efficient tuning mechanism on ControlNet. It also integrates a film encoder adept at understanding the film's semantic depth, emotional impact, and aesthetic appeal. Additionally, we introduce a novel, effective yet straightforward evaluation metric to evaluate the originality and recognizability of music within film scores. To fill this gap for film scores, we curate a comprehensive dataset of film videos and legendary original scores, injecting domain-specific knowledge into our data-driven generation model. Our model outperforms existing methodologies in creating film scores, capable of generating music that reflects the guidance of a maestro's style, thereby redefining the benchmark for automated film scores and laying a robust groundwork for future research in this domain. The code and generated samples are available at //anonymous.4open.science/r/HPM.
Understanding identifiability of latent content and style variables from unaligned multi-domain data is essential for tasks such as domain translation and data generation. Existing works on content-style identification were often developed under somewhat stringent conditions, e.g., that all latent components are mutually independent and that the dimensions of the content and style variables are known. We introduce a new analytical framework via cross-domain \textit{latent distribution matching} (LDM), which establishes content-style identifiability under substantially more relaxed conditions. Specifically, we show that restrictive assumptions such as component-wise independence of the latent variables can be removed. Most notably, we prove that prior knowledge of the content and style dimensions is not necessary for ensuring identifiability, if sparsity constraints are properly imposed onto the learned latent representations. Bypassing the knowledge of the exact latent dimension has been a longstanding aspiration in unsupervised representation learning -- our analysis is the first to underpin its theoretical and practical viability. On the implementation side, we recast the LDM formulation into a regularized multi-domain GAN loss with coupled latent variables. We show that the reformulation is equivalent to LDM under mild conditions -- yet requiring considerably less computational resource. Experiments corroborate with our theoretical claims.
Existing large vision-language models (LVLMs) are largely limited to processing short, seconds-long videos and struggle with generating coherent descriptions for extended video spanning minutes or more. Long video description introduces new challenges, such as plot-level consistency across descriptions. To address these, we figure out audio-visual character identification, matching character names to each dialogue, as a key factor. We propose StoryTeller, a system for generating dense descriptions of long videos, incorporating both low-level visual concepts and high-level plot information. StoryTeller uses a multimodal large language model that integrates visual, audio, and text modalities to perform audio-visual character identification on minute-long video clips. The results are then fed into a LVLM to enhance consistency of video description. We validate our approach on movie description tasks and introduce MovieStory101, a dataset with dense descriptions for three-minute movie clips. To evaluate long video descriptions, we create MovieQA, a large set of multiple-choice questions for the MovieStory101 test set. We assess descriptions by inputting them into GPT-4 to answer these questions, using accuracy as an automatic evaluation metric. Experiments show that StoryTeller outperforms all open and closed-source baselines on MovieQA, achieving 9.5% higher accuracy than the strongest baseline, Gemini-1.5-pro, and demonstrating a +15.56% advantage in human side-by-side evaluations. Additionally, incorporating audio-visual character identification from StoryTeller improves the performance of all video description models, with Gemini-1.5-pro and GPT-4o showing relative improvement of 5.5% and 13.0%, respectively, in accuracy on MovieQA.
Video question-answering (QA) is a core task in video understanding. Evaluating the quality of video QA and video caption data quality for training video large language models (VideoLLMs) is an essential challenge. Although various methods have been proposed for assessing video caption quality, there remains a lack of dedicated evaluation methods for Video QA. To address this gap, we introduce EVQAScore, a reference-free method that leverages keyword extraction to assess both video caption and video QA data quality. Additionally, we incorporate frame sampling and rescaling techniques to enhance the efficiency and robustness of our evaluation, this enables our score to evaluate the quality of extremely long videos. Our approach achieves state-of-the-art (SOTA) performance (32.8 for Kendall correlation and 42.3 for Spearman correlation, 4.7 and 5.9 higher than the previous method PAC-S++) on the VATEX-EVAL benchmark for video caption evaluation. Furthermore, by using EVQAScore for data selection, we achieved SOTA results with only 12.5\% of the original data volume, outperforming the previous SOTA method PAC-S and 100\% of data.
Content-creator collaborations are a widespread strategy for enhancing digital viewership and revenue. While existing research has explored the efficacy of collaborations, few have looked at inequities in collaborations, particularly from the perspective of the supply and demand of attention. Leveraging 42,376 videos and 6,117,441 comments from YouTube (across 150 channels and 3 games), this study examines gender inequality in collaborative environments. Utilizing Shapley value, a tool from cooperative game theory, results reveal dominant in-group collaborations based on in-game affordances. However, audience responses are aligned across games, reflecting symmetric biases across the gaming communities, with comments focusing more on peripherals than actual gameplay for women. We find supply-side asymmetries exist along with demand-side symmetries. Our results engage with the larger literature on digital and online biases, highlighting how genre and affordances moderate gendered collaboration, the direction of inequality, and contributing a general framework to quantify synergy across collaborations.
Short video platforms, such as YouTube, Instagram, or TikTok, are used by billions of users globally. These platforms expose users to harmful content, ranging from clickbait or physical harms to misinformation or online hate. Yet, detecting harmful videos remains challenging due to an inconsistent understanding of what constitutes harm and limited resources and mental tolls involved in human annotation. As such, this study advances measures and methods to detect harm in video content. First, we develop a comprehensive taxonomy for online harm on video platforms, categorizing it into six categories: Information, Hate and harassment, Addictive, Clickbait, Sexual, and Physical harms. Next, we establish multimodal large language models as reliable annotators of harmful videos. We analyze 19,422 YouTube videos using 14 image frames, 1 thumbnail, and text metadata, comparing the accuracy of crowdworkers (Mturk) and GPT-4-Turbo with domain expert annotations serving as the gold standard. Our results demonstrate that GPT-4-Turbo outperforms crowdworkers in both binary classification (harmful vs. harmless) and multi-label harm categorization tasks. Methodologically, this study extends the application of LLMs to multi-label and multi-modal contexts beyond text annotation and binary classification. Practically, our study contributes to online harm mitigation by guiding the definitions and identification of harmful content on video platforms.
While large language models (LLMs) have demonstrated remarkable capabilities across a range of downstream tasks, a significant concern revolves around their propensity to exhibit hallucinations: LLMs occasionally generate content that diverges from the user input, contradicts previously generated context, or misaligns with established world knowledge. This phenomenon poses a substantial challenge to the reliability of LLMs in real-world scenarios. In this paper, we survey recent efforts on the detection, explanation, and mitigation of hallucination, with an emphasis on the unique challenges posed by LLMs. We present taxonomies of the LLM hallucination phenomena and evaluation benchmarks, analyze existing approaches aiming at mitigating LLM hallucination, and discuss potential directions for future research.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191