Event cameras offer low-power visual sensing capabilities ideal for edge-device applications. However, their high event rate, driven by high temporal details, can be restrictive in terms of bandwidth and computational resources. In edge AI applications, determining the minimum amount of events for specific tasks can allow reducing the event rate to improve bandwidth, memory, and processing efficiency. In this paper, we study the effect of event subsampling on the accuracy of event data classification using convolutional neural network (CNN) models. Surprisingly, across various datasets, the number of events per video can be reduced by an order of magnitude with little drop in accuracy, revealing the extent to which we can push the boundaries in accuracy vs. event rate trade-off. Additionally, we also find that lower classification accuracy in high subsampling rates is not solely attributable to information loss due to the subsampling of the events, but that the training of CNNs can be challenging in highly subsampled scenarios, where the sensitivity to hyperparameters increases. We quantify training instability across multiple event-based classification datasets using a novel metric for evaluating the hyperparameter sensitivity of CNNs in different subsampling settings. Finally, we analyze the weight gradients of the network to gain insight into this instability.
Given a video with $T$ frames, frame sampling is a task to select $N \ll T$ frames, so as to maximize the performance of a fixed video classifier. Not just brute-force search, but most existing methods suffer from its vast search space of $\binom{T}{N}$, especially when $N$ gets large. To address this challenge, we introduce a novel perspective of reducing the search space from $O(T^N)$ to $O(T)$. Instead of exploring the entire $O(T^N)$ space, our proposed semi-optimal policy selects the top $N$ frames based on the independently estimated value of each frame using per-frame confidence, significantly reducing the computational complexity. We verify that our semi-optimal policy can efficiently approximate the optimal policy, particularly under practical settings. Additionally, through extensive experiments on various datasets and model architectures, we demonstrate that learning our semi-optimal policy ensures stable and high performance regardless of the size of $N$ and $T$.
Spiking Neural Networks (SNNs) have emerged as a promising substitute for Artificial Neural Networks (ANNs) due to their advantages of fast inference and low power consumption. However, the lack of efficient training algorithms has hindered their widespread adoption. Even efficient ANN-SNN conversion methods necessitate quantized training of ANNs to enhance the effectiveness of the conversion, incurring additional training costs. To address these challenges, we propose an efficient ANN-SNN conversion framework with only inference scale complexity. The conversion framework includes a local threshold balancing algorithm, which enables efficient calculation of the optimal thresholds and fine-grained adjustment of the threshold value by channel-wise scaling. We also introduce an effective delayed evaluation strategy to mitigate the influence of the spike propagation delays. We demonstrate the scalability of our framework in typical computer vision tasks: image classification, semantic segmentation, object detection, and video classification. Our algorithm outperforms existing methods, highlighting its practical applicability and efficiency. Moreover, we have evaluated the energy consumption of the converted SNNs, demonstrating their superior low-power advantage compared to conventional ANNs. This approach simplifies the deployment of SNNs by leveraging open-source pre-trained ANN models, enabling fast, low-power inference with negligible performance reduction. Code is available at https://github.com/putshua/Inference-scale-ANN-SNN.
Spiking Neural Networks (SNNs) have emerged as a compelling, energy-efficient alternative to traditional Artificial Neural Networks (ANNs) for static image tasks such as image classification and segmentation. However, in the more complex video classification domain, SNN-based methods fall considerably short of ANN-based benchmarks due to the challenges in processing dense frame sequences. To bridge this gap, we propose ReSpike, a hybrid framework that synergizes the strengths of ANNs and SNNs to tackle action recognition tasks with high accuracy and low energy cost. By decomposing film clips into spatial and temporal components, i.e., RGB image Key Frames and event-like Residual Frames, ReSpike leverages ANN for learning spatial information and SNN for learning temporal information. In addition, we propose a multi-scale cross-attention mechanism for effective feature fusion. Compared to state-of-the-art SNN baselines, our ReSpike hybrid architecture demonstrates significant performance improvements (e.g., >30% absolute accuracy improvement on HMDB-51, UCF-101, and Kinetics-400). Furthermore, ReSpike achieves comparable performance with prior ANN approaches while bringing better accuracy-energy tradeoff.
Existing research often treats long-form videos as extended short videos, leading to several limitations: inadequate capture of long-range dependencies, inefficient processing of redundant information, and failure to extract high-level semantic concepts. To address these issues, we propose a novel approach that more accurately reflects human cognition. This paper introduces HERMES: temporal-coHERent long-forM understanding with Episodes and Semantics, a model that simulates episodic memory accumulation to capture action sequences and reinforces them with semantic knowledge dispersed throughout the video. Our work makes two key contributions: First, we develop an Episodic COmpressor (ECO) that efficiently aggregates crucial representations from micro to semi-macro levels, overcoming the challenge of long-range dependencies. Second, we propose a Semantics ReTRiever (SeTR) that enhances these aggregated representations with semantic information by focusing on the broader context, dramatically reducing feature dimensionality while preserving relevant macro-level information. This addresses the issues of redundancy and lack of high-level concept extraction. Extensive experiments demonstrate that HERMES achieves state-of-the-art performance across multiple long-video understanding benchmarks in both zero-shot and fully-supervised settings.
Exploiting both audio and visual modalities for video classification is a challenging task, as the existing methods require large model architectures, leading to high computational complexity and resource requirements. Smaller architectures, on the other hand, struggle to achieve optimal performance. In this paper, we propose Attend-Fusion, an audio-visual (AV) fusion approach that introduces a compact model architecture specifically designed to capture intricate audio-visual relationships in video data. Through extensive experiments on the challenging YouTube-8M dataset, we demonstrate that Attend-Fusion achieves an F1 score of 75.64\% with only 72M parameters, which is comparable to the performance of larger baseline models such as Fully-Connected Late Fusion (75.96\% F1 score, 341M parameters). Attend-Fusion achieves similar performance to the larger baseline model while reducing the model size by nearly 80\%, highlighting its efficiency in terms of model complexity. Our work demonstrates that the Attend-Fusion model effectively combines audio and visual information for video classification, achieving competitive performance with significantly reduced model size. This approach opens new possibilities for deploying high-performance video understanding systems in resource-constrained environments across various applications.
Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Therefore, a deep understanding of adversarial attacks can better respond to emergency situations. In order to improve attack performance, many style-transfer-based attacks and patch-based attacks have been proposed. However, the global perturbation of the former will bring unnatural global color, while the latter is difficult to achieve success in targeted attacks due to the limited perturbation space. Moreover, compared to a plethora of methods targeting image classifiers, video adversarial attacks are still not that popular. Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA). SLA is conducted through three steps. The first step involves building a style references set for logos, which can not only make the generated examples more natural, but also carry more target class features in the targeted attacks. Then, reinforcement learning (RL) is employed to determine the style reference and position parameters of the logo within the video, which ensures that the stylized logo is placed in the video with optimal attributes. Finally, perturbation optimization is designed to optimize perturbations to improve the fooling rate in a step-by-step manner. Sufficient experimental results indicate that, SLA can achieve better performance than state-of-the-art methods and still maintain good deception effects when facing various defense methods.
Hate speech is a pressing issue in modern society, with significant effects both online and offline. Recent research in hate speech detection has primarily centered on text-based media, largely overlooking multimodal content such as videos. Existing studies on hateful video datasets have predominantly focused on English content within a Western context and have been limited to binary labels (hateful or non-hateful), lacking detailed contextual information. This study presents MultiHateClip1 , an novel multilingual dataset created through hate lexicons and human annotation. It aims to enhance the detection of hateful videos on platforms such as YouTube and Bilibili, including content in both English and Chinese languages. Comprising 2,000 videos annotated for hatefulness, offensiveness, and normalcy, this dataset provides a cross-cultural perspective on gender-based hate speech. Through a detailed examination of human annotation results, we discuss the differences between Chinese and English hateful videos and underscore the importance of different modalities in hateful and offensive video analysis. Evaluations of state-of-the-art video classification models, such as VLM, GPT-4V and Qwen-VL, on MultiHateClip highlight the existing challenges in accurately distinguishing between hateful and offensive content and the urgent need for models that are both multimodally and culturally nuanced. MultiHateClip represents a foundational advance in enhancing hateful video detection by underscoring the necessity of a multimodal and culturally sensitive approach in combating online hate speech.
In the domain of black-box model extraction, conventional methods reliant on soft labels or surrogate datasets struggle with scaling to high-dimensional input spaces and managing the complexity of an extensive array of interrelated classes. In this work, we present a novel approach that utilizes SHAP (SHapley Additive exPlanations) to enhance synthetic data generation. SHAP quantifies the individual contributions of each input feature towards the victim model's output, facilitating the optimization of an energy-based GAN towards a desirable output. This method significantly boosts performance, achieving a 16.45% increase in the accuracy of image classification models and extending to video classification models with an average improvement of 26.11% and a maximum of 33.36% on challenging datasets such as UCF11, UCF101, Kinetics 400, Kinetics 600, and Something-Something V2. We further demonstrate the effectiveness and practical utility of our method under various scenarios, including the availability of top-k prediction probabilities, top-k prediction labels, and top-1 labels.
Narrative videos, such as movies, pose significant challenges in video understanding due to their rich contexts (characters, dialogues, storylines) and diverse demands (identify who, relationship, and reason). In this paper, we introduce MovieSeq, a multimodal language model developed to address the wide range of challenges in understanding video contexts. Our core idea is to represent videos as interleaved multimodal sequences (including images, plots, videos, and subtitles), either by linking external knowledge databases or using offline models (such as whisper for subtitles). Through instruction-tuning, this approach empowers the language model to interact with videos using interleaved multimodal instructions. For example, instead of solely relying on video as input, we jointly provide character photos alongside their names and dialogues, allowing the model to associate these elements and generate more comprehensive responses. To demonstrate its effectiveness, we validate MovieSeq's performance on six datasets (LVU, MAD, Movienet, CMD, TVC, MovieQA) across five settings (video classification, audio description, video-text retrieval, video captioning, and video question-answering). The code will be public at https://github.com/showlab/MovieSeq.
Previous deepfake detection methods mostly depend on low-level textural features vulnerable to perturbations and fall short of detecting unseen forgery methods. In contrast, high-level semantic features are less susceptible to perturbations and not limited to forgery-specific artifacts, thus having stronger generalization. Motivated by this, we propose a detection method that utilizes high-level semantic features of faces to identify inconsistencies in temporal domain. We introduce UniForensics, a novel deepfake detection framework that leverages a transformer-based video classification network, initialized with a meta-functional face encoder for enriched facial representation. In this way, we can take advantage of both the powerful spatio-temporal model and the high-level semantic information of faces. Furthermore, to leverage easily accessible real face data and guide the model in focusing on spatio-temporal features, we design a Dynamic Video Self-Blending (DVSB) method to efficiently generate training samples with diverse spatio-temporal forgery traces using real facial videos. Based on this, we advance our framework with a two-stage training approach: The first stage employs a novel self-supervised contrastive learning, where we encourage the network to focus on forgery traces by impelling videos generated by the same forgery process to have similar representations. On the basis of the representation learned in the first stage, the second stage involves fine-tuning on face forgery detection dataset to build a deepfake detector. Extensive experiments validates that UniForensics outperforms existing face forgery methods in generalization ability and robustness. In particular, our method achieves 95.3\% and 77.2\% cross dataset AUC on the challenging Celeb-DFv2 and DFDC respectively.
Vision Transformers (ViT) have emerged as the de-facto choice for numerous industry grade vision solutions. But their inference cost can be prohibitive for many settings, as they compute self-attention in each layer which suffers from quadratic computational complexity in the number of tokens. On the other hand, spatial information in images and spatio-temporal information in videos is usually sparse and redundant. In this work, we introduce LookupViT, that aims to exploit this information sparsity to reduce ViT inference cost. LookupViT provides a novel general purpose vision transformer block that operates by compressing information from higher resolution tokens to a fixed number of tokens. These few compressed tokens undergo meticulous processing, while the higher-resolution tokens are passed through computationally cheaper layers. Information sharing between these two token sets is enabled through a bidirectional cross-attention mechanism. The approach offers multiple advantages - (a) easy to implement on standard ML accelerators (GPUs/TPUs) via standard high-level operators, (b) applicable to standard ViT and its variants, thus generalizes to various tasks, (c) can handle different tokenization and attention approaches. LookupViT also offers flexibility for the compressed tokens, enabling performance-computation trade-offs in a single trained model. We show LookupViT's effectiveness on multiple domains - (a) for image-classification (ImageNet-1K and ImageNet-21K), (b) video classification (Kinetics400 and Something-Something V2), (c) image captioning (COCO-Captions) with a frozen encoder. LookupViT provides $2\times$ reduction in FLOPs while upholding or improving accuracy across these domains. In addition, LookupViT also demonstrates out-of-the-box robustness and generalization on image classification (ImageNet-C,R,A,O), improving by up to $4\%$ over ViT.
Face Forgery videos have elicited critical social public concerns and various detectors have been proposed. However, fully-supervised detectors may lead to easily overfitting to specific forgery methods or videos, and existing self-supervised detectors are strict on auxiliary tasks, such as requiring audio or multi-modalities, leading to limited generalization and robustness. In this paper, we examine whether we can address this issue by leveraging visual-only real face videos. To this end, we propose to learn the Natural Consistency representation (NACO) of real face videos in a self-supervised manner, which is inspired by the observation that fake videos struggle to maintain the natural spatiotemporal consistency even under unknown forgery methods and different perturbations. Our NACO first extracts spatial features of each frame by CNNs then integrates them into Transformer to learn the long-range spatiotemporal representation, leveraging the advantages of CNNs and Transformer on local spatial receptive field and long-term memory respectively. Furthermore, a Spatial Predictive Module~(SPM) and a Temporal Contrastive Module~(TCM) are introduced to enhance the natural consistency representation learning. The SPM aims to predict random masked spatial features from spatiotemporal representation, and the TCM regularizes the latent distance of spatiotemporal representation by shuffling the natural order to disturb the consistency, which could both force our NACO more sensitive to the natural spatiotemporal consistency. After the representation learning stage, a MLP head is fine-tuned to perform the usual forgery video classification task. Extensive experiments show that our method outperforms other state-of-the-art competitors with impressive generalization and robustness.
Pre-trained vision-language models (VLMs) have enabled significant progress in open vocabulary computer vision tasks such as image classification, object detection and image segmentation. Some recent works have focused on extending VLMs to open vocabulary single label action classification in videos. However, previous methods fall short in holistic video understanding which requires the ability to simultaneously recognize multiple actions and entities e.g., objects in the video in an open vocabulary setting. We formulate this problem as open vocabulary multilabel video classification and propose a method to adapt a pre-trained VLM such as CLIP to solve this task. We leverage large language models (LLMs) to provide semantic guidance to the VLM about class labels to improve its open vocabulary performance with two key contributions. First, we propose an end-to-end trainable architecture that learns to prompt an LLM to generate soft attributes for the CLIP text-encoder to enable it to recognize novel classes. Second, we integrate a temporal modeling module into CLIP's vision encoder to effectively model the spatio-temporal dynamics of video concepts as well as propose a novel regularized finetuning technique to ensure strong open vocabulary classification performance in the video domain. Our extensive experimentation showcases the efficacy of our approach on multiple benchmark datasets.
Deepfake techniques generate highly realistic data, making it challenging for humans to discern between actual and artificially generated images. Recent advancements in deep learning-based deepfake detection methods, particularly with diffusion models, have shown remarkable progress. However, there is a growing demand for real-world applications to detect unseen individuals, deepfake techniques, and scenarios. To address this limitation, we propose a Prototype-based Unified Framework for Deepfake Detection (PUDD). PUDD offers a detection system based on similarity, comparing input data against known prototypes for video classification and identifying potential deepfakes or previously unseen classes by analyzing drops in similarity. Our extensive experiments reveal three key findings: (1) PUDD achieves an accuracy of 95.1% on Celeb-DF, outperforming state-of-the-art deepfake detection methods; (2) PUDD leverages image classification as the upstream task during training, demonstrating promising performance in both image classification and deepfake detection tasks during inference; (3) PUDD requires only 2.7 seconds for retraining on new data and emits 10$^{5}$ times less carbon compared to the state-of-the-art model, making it significantly more environmentally friendly.
Recent advancements in Machine Unlearning (MU) have introduced solutions to selectively remove certain training samples, such as those with outdated or sensitive information, from trained models. Despite these advancements, evaluation of MU methods have been inconsistent, employing different trained models and architectures, and sample removal strategies, which hampers accurate comparison. In addition, prior MU approaches have mainly focused on singular tasks or modalities, which is not comprehensive. To address these limitations, we develop MU-Bench, the first comprehensive benchmark for MU that (i) unifies the sets of deleted samples and trained models, and (ii) provides broad coverage of tasks and data modalities, including previously unexplored domains such as speech and video classification. Our evaluation show that RandLabel and SalUn are the most effective general MU approaches on MU-Bench, and BadT and SCRUB are capable of achieving random performance on the deletion set. We analyze several under-investigated aspects of unlearning, including scalability, the impacts of parameter-efficient fine-tuning and curriculum learning, and susceptibility to dataset biases. MU-Bench provides an easy-to-use package that includes dataset splits, models, and implementations, together with a leader board to enable unified and scalable MU research.
Video processing is generally divided into two main categories: processing of the entire video, which typically yields optimal classification outcomes, and real-time processing, where the objective is to make a decision as promptly as possible. The latter is often driven by the need to identify rapidly potential critical or dangerous situations. These could include machine failure, traffic accidents, heart problems, or dangerous behavior. Although the models dedicated to the processing of entire videos are typically well-defined and clearly presented in the literature, this is not the case for online processing, where a plethora of hand-devised methods exist. To address this, we present \our{}, a novel, unified, and theoretically-based adaptation framework for dealing with the online classification problem for video data. The initial phase of our study is to establish a robust mathematical foundation for the theory of classification of sequential data, with the potential to make a decision at an early stage. This allows us to construct a natural function that encourages the model to return an outcome much faster. The subsequent phase is to demonstrate a straightforward and readily implementable method for adapting offline models to online and recurrent operations. Finally, by comparing the proposed approach to the non-online state-of-the-art baseline, it is demonstrated that the use of \our{} encourages the network to make earlier classification decisions without compromising accuracy.
Human action recognition in dark videos is a challenging task for computer vision. Recent research focuses on applying dark enhancement methods to improve the visibility of the video. However, such video processing results in the loss of critical information in the original (un-enhanced) video. Conversely, traditional two-stream methods are capable of learning information from both original and processed videos, but it can lead to a significant increase in the computational cost during the inference phase in the task of video classification. To address these challenges, we propose a novel teacher-student video classification framework, named Dual-Light KnowleDge Distillation for Action Recognition in the Dark (DL-KDD). This framework enables the model to learn from both original and enhanced video without introducing additional computational cost during inference. Specifically, DL-KDD utilizes the strategy of knowledge distillation during training. The teacher model is trained with enhanced video, and the student model is trained with both the original video and the soft target generated by the teacher model. This teacher-student framework allows the student model to predict action using only the original input video during inference. In our experiments, the proposed DL-KDD framework outperforms state-of-the-art methods on the ARID, ARID V1.5, and Dark-48 datasets. We achieve the best performance on each dataset and up to a 4.18% improvement on Dark-48, using only original video inputs, thus avoiding the use of two-stream framework or enhancement modules for inference. We further validate the effectiveness of the distillation strategy in ablative experiments. The results highlight the advantages of our knowledge distillation framework in dark human action recognition.
Understanding Activities of Daily Living (ADLs) is a crucial step for different applications including assistive robots, smart homes, and healthcare. However, to date, few benchmarks and methods have focused on complex ADLs, especially those involving multi-person interactions in home environments. In this paper, we propose a new dataset and benchmark, InteractADL, for understanding complex ADLs that involve interaction between humans (and objects). Furthermore, complex ADLs occurring in home environments comprise a challenging long-tailed distribution due to the rarity of multi-person interactions, and pose fine-grained visual recognition tasks due to the presence of semantically and visually similar classes. To address these issues, we propose a novel method for fine-grained few-shot video classification called Name Tuning that enables greater semantic separability by learning optimal class name vectors. We show that Name Tuning can be combined with existing prompt tuning strategies to learn the entire input text (rather than only learning the prompt or class names) and demonstrate improved performance for few-shot classification on InteractADL and 4 other fine-grained visual classification benchmarks. For transparency and reproducibility, we release our code at https://github.com/zanedurante/vlm_benchmark.
In an era of rapidly evolving internet technology, the surge in multimodal content, including videos, has expanded the horizons of online communication. However, the detection of toxic content in this diverse landscape, particularly in low-resource code-mixed languages, remains a critical challenge. While substantial research has addressed toxic content detection in textual data, the realm of video content, especially in non-English languages, has been relatively underexplored. This paper addresses this research gap by introducing a benchmark dataset, the first of its kind, consisting of 931 videos with 4021 code-mixed Hindi-English utterances collected from YouTube. Each utterance within this dataset has been meticulously annotated for toxicity, severity, and sentiment labels. We have developed an advanced Multimodal Multitask framework built for Toxicity detection in Video Content by leveraging Language Models (LMs), crafted for the primary objective along with the additional tasks of conducting sentiment and severity analysis. ToxVidLM incorporates three key modules - the Encoder module, Cross-Modal Synchronization module, and Multitask module - crafting a generic multimodal LM customized for intricate video classification tasks. Our experiments reveal that incorporating multiple modalities from the videos substantially enhances the performance of toxic content detection by achieving an Accuracy and Weighted F1 score of 94.29% and 94.35%, respectively.