Bing Fan

Bing Fan, Yunhe Feng, Yapeng Tian et al.

Egocentric visual query localization (EgoVQL) focuses on localizing the target of interest in space and time from first-person videos, given a visual query. Despite recent progressive, existing methods often struggle to handle severe object appearance changes and cluttering background in the video due to lacking sufficient target cues, leading to degradation. Addressing this, we introduce PRVQL, a novel Progressive knowledge-guided Refinement framework for EgoVQL. The core is to continuously exploit target-relevant knowledge directly from videos and utilize it as guidance to refine both query and video features for improving target localization. Our PRVQL contains multiple processing stages. The target knowledge from one stage, comprising appearance and spatial knowledge extracted via two specially designed knowledge learning modules, are utilized as guidance to refine the query and videos features for the next stage, which are used to generate more accurate knowledge for further feature refinement. With such a progressive process, target knowledge in PRVQL can be gradually improved, which, in turn, leads to better refined query and video features for localization in the final stage. Compared to previous methods, our PRVQL, besides the given object cues, enjoys additional crucial target information from a video as guidance to refine features, and hence enhances EgoVQL in complicated scenes. In our experiments on challenging Ego4D, PRVQL achieves state-of-the-art result and largely surpasses other methods, showing its efficacy. Our code, model and results will be released at https://github.com/fb-reps/PRVQL.

Xin Gu, Bing Fan, Jiali Yao et al.

In real scenarios, videos can span several minutes or even hours. However, existing research on spatio-temporal video grounding (STVG), given a textual query, mainly focuses on localizing targets in short videos of tens of seconds, typically less than one minute, which limits real-world applications. In this paper, we explore Long-Form STVG (LF-STVG), which aims to locate targets in long-term videos. Compared with short videos, long-term videos contain much longer temporal spans and more irrelevant information, making it difficult for existing STVG methods that process all frames at once. To address this challenge, we propose an AutoRegressive Transformer architecture for LF-STVG, termed ART-STVG. Unlike conventional STVG methods that require the entire video sequence to make predictions at once, ART-STVG treats the video as streaming input and processes frames sequentially, enabling efficient handling of long videos. To model spatio-temporal context, we design spatial and temporal memory banks and apply them to the decoders. Since memories from different moments are not always relevant to the current frame, we introduce simple yet effective memory selection strategies to provide more relevant information to the decoders, significantly improving performance. Furthermore, instead of parallel spatial and temporal localization, we propose a cascaded spatio-temporal design that connects the spatial decoder to the temporal decoder, allowing fine-grained spatial cues to assist complex temporal localization in long videos. Experiments on newly extended LF-STVG datasets show that ART-STVG significantly outperforms state-of-the-art methods, while achieving competitive performance on conventional short-form STVG.

Jiali Yao, Xinran Deng, Xin Gu et al.

In this paper, we propose spatio-temporal omni-object video grounding, dubbed OmniSTVG, a new STVG task that aims at localizing spatially and temporally all targets mentioned in the textual query from videos. Compared to classic STVG locating only a single target, OmniSTVG enables localization of not only an arbitrary number of text-referred targets but also their interacting counterparts in the query from the video, making it more flexible and practical in real scenarios for comprehensive understanding. In order to facilitate exploration of OmniSTVG, we introduce BOSTVG, a large-scale benchmark dedicated to OmniSTVG. Specifically, our BOSTVG consists of 10,018 videos with 10.2M frames and covers a wide selection of 287 classes from diverse scenarios. Each sequence in BOSTVG, paired with a free-form textual query, encompasses a varying number of targets ranging from 1 to 10. To ensure high quality, each video is manually annotated with meticulous inspection and refinement. To our best knowledge, BOSTVG is to date the first and the largest benchmark for OmniSTVG. To encourage future research, we introduce a simple yet effective approach, named OmniTube, which, drawing inspiration from Transformer-based STVG methods, is specially designed for OmniSTVG and demonstrates promising results. By releasing BOSTVG, we hope to go beyond classic STVG by locating every object appearing in the query for more comprehensive understanding, opening up a new direction for STVG. Our benchmark, model, and results will be released at https://github.com/JellyYao3000/OmniSTVG.

Bing Fan, Shu Hu, Feng Ding

DeepFake, an AI technology for creating facial forgeries, has garnered global attention. Amid such circumstances, forensics researchers focus on developing defensive algorithms to counter these threats. In contrast, there are techniques developed for enhancing the aggressiveness of DeepFake, e.g., through anti-forensics attacks, to disrupt forensic detectors. However, such attacks often sacrifice image visual quality for improved undetectability. To address this issue, we propose a method to generate novel adversarial sharpening masks for launching black-box anti-forensics attacks. Unlike many existing arts, with such perturbations injected, DeepFakes could achieve high anti-forensics performance while exhibiting pleasant sharpening visual effects. After experimental evaluations, we prove that the proposed method could successfully disrupt the state-of-the-art DeepFake detectors. Besides, compared with the images processed by existing DeepFake anti-forensics methods, the visual qualities of anti-forensics DeepFakes rendered by the proposed method are significantly refined.

Yue Zhou, Xinan He, Kaiqing Lin et al.

While specialized detectors for AI-generated images excel on curated benchmarks, they fail catastrophically in real-world scenarios, as evidenced by their critically high false-negative rates on `in-the-wild' benchmarks. Instead of crafting another specialized `knife' for this problem, we bring a `gun' to the fight: a simple linear classifier on a modern Vision Foundation Model (VFM). Trained on identical data, this baseline decisively `outguns' bespoke detectors, boosting in-the-wild accuracy by a striking margin of over 20\%. Our analysis pinpoints the source of the VFM's `firepower': First, by probing text-image similarities, we find that recent VLMs (e.g., Perception Encoder, Meta CLIP2) have learned to align synthetic images with forgery-related concepts (e.g., `AI-generated'), unlike previous versions. Second, we speculate that this is due to data exposure, as both this alignment and overall accuracy plummet on a novel dataset scraped after the VFM's pre-training cut-off date, ensuring it was unseen during pre-training. Our findings yield two critical conclusions: 1) For the real-world `gunfight' of AI-generated image detection, the raw `firepower' of an updated VFM is far more effective than the `craftsmanship' of a static detector. 2) True generalization evaluation requires test data to be independent of the model's entire training history, including pre-training.

Bing Fan, Shusen Ma, Yun-Bo Zhao et al.

In multivariate time series forecasting (MTSF), existing strategies for processing sequences are typically categorized as channel-independent and channel-mixing. The former treats all temporal information of each variable as a token, focusing on capturing local temporal features of individual variables, while the latter constructs a token from the multivariate information at each time step, emphasizing the modeling of global temporal dependencies. Current mainstream models are mostly based on Transformer and the emerging Mamba. Transformers excel at modeling global dependencies through self-attention mechanisms but exhibit limited sensitivity to local temporal patterns and suffer from quadratic computational complexity, restricting their efficiency in long-sequence processing. In contrast, Mamba, based on state space models (SSMs), achieves linear complexity and efficient long-range modeling but struggles to aggregate global contextual information in parallel. To overcome the limitations of both models, we propose DC-Mamber, a dual-channel forecasting model based on Mamba and linear Transformer for time series forecasting. Specifically, the Mamba-based channel employs a channel-independent strategy to extract intra-variable features, while the Transformer-based channel adopts a channel-mixing strategy to model cross-timestep global dependencies. DC-Mamber first maps the raw input into two distinct feature representations via separate embedding layers. These representations are then processed by a variable encoder (built on Mamba) and a temporal encoder (built on linear Transformer), respectively. Finally, a fusion layer integrates the dual-channel features for prediction. Extensive experiments on eight public datasets confirm DC-Mamber's superior accuracy over existing models.