WorldSimBench: Towards Video Generation Models as World Simulators

Recent advancements in predictive models have demonstrated exceptional capabilities in predicting the future state of objects and scenes. However, the lack of categorization based on inherent characteristics continues to hinder the progress of predictive model development. Additionally, existing benchmarks are unable to effectively evaluate higher-capability, highly embodied predictive models from an embodied perspective. In this work, we classify the functionalities of predictive models into a hierarchy and take the first step in evaluating World Simulators by proposing a dual evaluation framework called WorldSimBench. WorldSimBench includes Explicit Perceptual Evaluation and Implicit Manipulative Evaluation, encompassing human preference assessments from the visual perspective and action-level evaluations in embodied tasks, covering three representative embodied scenarios: Open-Ended Embodied Environment, Autonomous, Driving, and Robot Manipulation. In the Explicit Perceptual Evaluation, we introduce the HF-Embodied Dataset, a video assessment dataset based on fine-grained human feedback, which we use to train a Human Preference Evaluator that aligns with human perception and explicitly assesses the visual fidelity of World Simulators. In the Implicit Manipulative Evaluation, we assess the video-action consistency of World Simulators by evaluating whether the generated situation-aware video can be accurately translated into the correct control signals in dynamic environments. Our comprehensive evaluation offers key insights that can drive further innovation in video generation models, positioning World Simulators as a pivotal advancement toward embodied artificial intelligence.

SOAR: Self-supervision Optimized UAV Action Recognition with Efficient Object-Aware Pretraining

We introduce SOAR, a novel Self-supervised pretraining algorithm for aerial footage captured by Unmanned Aerial Vehicles (UAVs). We incorporate human object knowledge throughout the pretraining process to enhance UAV video pretraining efficiency and downstream action recognition performance. This is in contrast to prior works that primarily incorporate object information during the fine-tuning stage. Specifically, we first propose a novel object-aware masking strategy designed to retain the visibility of certain patches related to objects throughout the pretraining phase. Second, we introduce an object-aware loss function that utilizes object information to adjust the reconstruction loss, preventing bias towards less informative background patches. In practice, SOAR with a vanilla ViT backbone, outperforms best UAV action recognition models, recording a 9.7% and 21.4% boost in top-1 accuracy on the NEC-Drone and UAV-Human datasets, while delivering an inference speed of 18.7ms per video, making it 2x to 5x faster. Additionally, SOAR obtains comparable accuracy to prior self-supervised learning (SSL) methods while requiring 87.5% less pretraining time and 25% less memory usage

Trustworthy Image Semantic Communication with GenAI: Explainablity, Controllability, and Efficiency

Image semantic communication (ISC) has garnered significant attention for its potential to achieve high efficiency in visual content transmission. However, existing ISC systems based on joint source-channel coding face challenges in interpretability, operability, and compatibility. To address these limitations, we propose a novel trustworthy ISC framework. This approach leverages text extraction and segmentation mapping techniques to convert images into explainable semantics, while employing Generative Artificial Intelligence (GenAI) for multiple downstream inference tasks. We also introduce a multi-rate ISC transmission protocol that dynamically adapts to both the received explainable semantic content and specific task requirements at the receiver. Simulation results demonstrate that our framework achieves explainable learning, decoupled training, and compatible transmission in various application scenarios. Finally, some intriguing research directions and application scenarios are identified.

AUTOHALLUSION: Automatic Generation of Hallucination Benchmarks for Vision-Language Models

Large vision-language models (LVLMs) hallucinate: certain context cues in an image may trigger the language module's overconfident and incorrect reasoning on abnormal or hypothetical objects. Though a few benchmarks have been developed to investigate LVLM hallucinations, they mainly rely on hand-crafted corner cases whose fail patterns may hardly generalize, and finetuning on them could undermine their validity. These motivate us to develop the first automatic benchmark generation approach, AUTOHALLUSION, that harnesses a few principal strategies to create diverse hallucination examples. It probes the language modules in LVLMs for context cues and uses them to synthesize images by: (1) adding objects abnormal to the context cues; (2) for two co-occurring objects, keeping one and excluding the other; or (3) removing objects closely tied to the context cues. It then generates image-based questions whose ground-truth answers contradict the language module's prior. A model has to overcome contextual biases and distractions to reach correct answers, while incorrect or inconsistent answers indicate hallucinations. AUTOHALLUSION enables us to create new benchmarks at the minimum cost and thus overcomes the fragility of hand-crafted benchmarks. It also reveals common failure patterns and reasons, providing key insights to detect, avoid, or control hallucinations. Comprehensive evaluations of top-tier LVLMs, e.g., GPT-4V(ision), Gemini Pro Vision, Claude 3, and LLaVA-1.5, show a 97.7% and 98.7% success rate of hallucination induction on synthetic and real-world datasets of AUTOHALLUSION, paving the way for a long battle against hallucinations.

Deep Stochastic Kinematic Models for Probabilistic Motion Forecasting in Traffic

Kinematic priors have shown to be helpful in boosting generalization and performance in prior work on trajectory forecasting. Specifically, kinematic priors have been applied such that models predict a set of actions instead of future output trajectories. By unrolling predicted trajectories via time integration and models of kinematic dynamics, predicted trajectories are not only kinematically feasible on average but also relate uncertainty from one timestep to the next. With benchmarks supporting prediction of multiple trajectory predictions, deterministic kinematic priors are less and less applicable to current models. We propose a method for integrating probabilistic kinematic priors into modern probabilistic trajectory forecasting architectures. The primary difference between our work and previous techniques is the analytical quantification of variance, or uncertainty, in predicted trajectories. With negligible additional computational overhead, our method can be generalized and easily implemented with any modern probabilistic method that models candidate trajectories as Gaussian distributions. In particular, our method works especially well in unoptimal settings, such as with small datasets or in the presence of noise. Our method achieves up to a 50% performance boost in small dataset settings and up to an 8% performance boost in large-scale learning compared to previous kinematic prediction methods on SOTA trajectory forecasting architectures out-of-the-box, with minimal fine-tuning. In this paper, we show four analytical formulations of probabilistic kinematic priors which can be used for any Gaussian Mixture Model (GMM)-based deep learning models, quantify the error bound on linear approximations applied during trajectory unrolling, and show results to evaluate each formulation in trajectory forecasting.

AGL-NET: Aerial-Ground Cross-Modal Global Localization with Varying Scales

We present AGL-NET, a novel learning-based method for global localization using LiDAR point clouds and satellite maps. AGL-NET tackles two critical challenges: bridging the representation gap between image and points modalities for robust feature matching, and handling inherent scale discrepancies between global view and local view. To address these challenges, AGL-NET leverages a unified network architecture with a novel two-stage matching design. The first stage extracts informative neural features directly from raw sensor data and performs initial feature matching. The second stage refines this matching process by extracting informative skeleton features and incorporating a novel scale alignment step to rectify scale variations between LiDAR and map data. Furthermore, a novel scale and skeleton loss function guides the network toward learning scale-invariant feature representations, eliminating the need for pre-processing satellite maps. This significantly improves real-world applicability in scenarios with unknown map scales. To facilitate rigorous performance evaluation, we introduce a meticulously designed dataset within the CARLA simulator specifically tailored for metric localization training and assessment. The code and dataset will be made publicly available.

A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models

Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs, such as unexpected artifacts and noises. To reduce these artifacts and enhance the perceptual quality of the results, in this paper, we propose a general method that can be effectively used in most GAN-based super-resolution (SR) models by introducing essential spatial information into the training process. We extract spatial information from the input data and incorporate it into the training loss, making the corresponding loss a spatially adaptive (SA) one. After that, we utilize it to guide the training process. We will show that the proposed approach is independent of the methods used to extract the spatial information and independent of the SR tasks and models. This method consistently guides the training process towards generating visually pleasing SR images and video frames, substantially mitigating artifacts and noise, ultimately leading to enhanced perceptual quality.

Real-World Atmospheric Turbulence Correction via Domain Adaptation

Atmospheric turbulence, a common phenomenon in daily life, is primarily caused by the uneven heating of the Earth's surface. This phenomenon results in distorted and blurred acquired images or videos and can significantly impact downstream vision tasks, particularly those that rely on capturing clear, stable images or videos from outdoor environments, such as accurately detecting or recognizing objects. Therefore, people have proposed ways to simulate atmospheric turbulence and designed effective deep learning-based methods to remove the atmospheric turbulence effect. However, these synthesized turbulent images can not cover all the range of real-world turbulence effects. Though the models have achieved great performance for synthetic scenarios, there always exists a performance drop when applied to real-world cases. Moreover, reducing real-world turbulence is a more challenging task as there are no clean ground truth counterparts provided to the models during training. In this paper, we propose a real-world atmospheric turbulence mitigation model under a domain adaptation framework, which links the supervised simulated atmospheric turbulence correction with the unsupervised real-world atmospheric turbulence correction. We will show our proposed method enhances performance in real-world atmospheric turbulence scenarios, improving both image quality and downstream vision tasks.

Adv-Diffusion: Imperceptible Adversarial Face Identity Attack via Latent Diffusion Model

Adversarial attacks involve adding perturbations to the source image to cause misclassification by the target model, which demonstrates the potential of attacking face recognition models. Existing adversarial face image generation methods still can't achieve satisfactory performance because of low transferability and high detectability. In this paper, we propose a unified framework Adv-Diffusion that can generate imperceptible adversarial identity perturbations in the latent space but not the raw pixel space, which utilizes strong inpainting capabilities of the latent diffusion model to generate realistic adversarial images. Specifically, we propose the identity-sensitive conditioned diffusion generative model to generate semantic perturbations in the surroundings. The designed adaptive strength-based adversarial perturbation algorithm can ensure both attack transferability and stealthiness. Extensive qualitative and quantitative experiments on the public FFHQ and CelebA-HQ datasets prove the proposed method achieves superior performance compared with the state-of-the-art methods without an extra generative model training process. The source code is available at https://github.com/kopper-xdu/Adv-Diffusion.

VLAP: Efficient Video-Language Alignment via Frame Prompting and Distilling for Video Question Answering

In this work, we propose an efficient Video-Language Alignment via Frame-Prompting and Distilling (VLAP) network. Our VLAP model addresses both efficient frame sampling and effective cross-modal alignment in a unified way. In our VLAP network, we design a new learnable question-aware Frame-Prompter together with a new cross-modal distillation (QFormer-Distiller) module. Pre-trained large image-language models have shown promising results on problems such as visual question answering. However, how to efficiently and effectively sample image frames when adapting pre-trained large image-language model to video-language alignment is still the major challenge. Compared with prior work, our VLAP model demonstrates the capability of selecting key frames with critical contents, thus improving the video-language alignment accuracy while reducing the inference latency (+3.3% on NExT-QA Temporal with 3.0X speed up). Overall, our VLAP network outperforms (e.g. +4.6% on STAR Interaction and +2.2% on STAR average with 3.0X speed up, ours 2-frames out-perform SeViLA 4-frames on VLEP with 4.2X speed up) the state-of-the-art methods on the video question-answering benchmarks.