Watching movies is one of the social activities typically done in groups. Emotion is the most vital factor that affects movie viewers' preferences. So, the emotional aspect of the movie needs to be determined and analyzed for further recommendations. It can be challenging to choose a movie that appeals to the emotions of a diverse group. Reaching an agreement for a group can be difficult due to the various genres and choices. This paper proposes a novel approach to group movie suggestions by examining emotions from three different channels: movie descriptions (text), soundtracks (audio), and posters (image). We employ the Jaccard similarity index to match each participant's emotional preferences to prospective movie choices, followed by a fuzzy inference technique to determine group consensus. We use a weighted integration process for the fusion of emotion scores from diverse data types. Then, group movie recommendation is based on prevailing emotions and viewers' best-loved movies. After determining the recommendations, the group's consensus level is calculated using a fuzzy inference system, taking participants' feedback as input. Participants (n=130) in the survey were provided with different emotion categories and asked to select the emotions best suited for particular movies (n=12). Comparison results between predicted and actual scores demonstrate the efficiency of using emotion detection for this problem (Jaccard similarity index = 0.76). We explored the relationship between induced emotions and movie popularity as an additional experiment, analyzing emotion distribution in 100 popular movies from the TMDB database. Such systems can potentially improve the accuracy of movie recommendation systems and achieve a high level of consensus among participants with diverse preferences.

Automated emotion recognition using electroencephalogram (EEG) signals has gained substantial attention. Although deep learning approaches exhibit strong performance, they often suffer from vulnerabilities to various perturbations, like environmental noise and adversarial attacks. In this paper, we propose an Inception feature generator and two-sided perturbation (INC-TSP) approach to enhance emotion recognition in brain-computer interfaces. INC-TSP integrates the Inception module for EEG data analysis and employs two-sided perturbation (TSP) as a defensive mechanism against input perturbations. TSP introduces worst-case perturbations to the model's weights and inputs, reinforcing the model's elasticity against adversarial attacks. The proposed approach addresses the challenge of maintaining accurate emotion recognition in the presence of input uncertainties. We validate INC-TSP in a subject-independent three-class emotion recognition scenario, demonstrating robust performance.

While recently Large Language Models (LLMs) have achieved remarkable successes, they are vulnerable to certain jailbreaking attacks that lead to generation of inappropriate or harmful content. Manual red-teaming requires finding adversarial prompts that cause such jailbreaking, e.g. by appending a suffix to a given instruction, which is inefficient and time-consuming. On the other hand, automatic adversarial prompt generation often leads to semantically meaningless attacks that can easily be detected by perplexity-based filters, may require gradient information from the TargetLLM, or do not scale well due to time-consuming discrete optimization processes over the token space. In this paper, we present a novel method that uses another LLM, called the AdvPrompter, to generate human-readable adversarial prompts in seconds, $\sim800\times$ faster than existing optimization-based approaches. We train the AdvPrompter using a novel algorithm that does not require access to the gradients of the TargetLLM. This process alternates between two steps: (1) generating high-quality target adversarial suffixes by optimizing the AdvPrompter predictions, and (2) low-rank fine-tuning of the AdvPrompter with the generated adversarial suffixes. The trained AdvPrompter generates suffixes that veil the input instruction without changing its meaning, such that the TargetLLM is lured to give a harmful response. Experimental results on popular open source TargetLLMs show state-of-the-art results on the AdvBench dataset, that also transfer to closed-source black-box LLM APIs. Further, we demonstrate that by fine-tuning on a synthetic dataset generated by AdvPrompter, LLMs can be made more robust against jailbreaking attacks while maintaining performance, i.e. high MMLU scores.

This study explores object detection in historical aerial photographs of Namibia to identify long-term environmental changes. Specifically, we aim to identify key objects -- Waterholes, Omuti homesteads, and Big trees -- around Oshikango in Namibia using sub-meter gray-scale aerial imagery from 1943 and 1972. In this work, we propose a workflow for analyzing historical aerial imagery using a deep semantic segmentation model on sparse hand-labels. To this end, we employ a number of strategies including class-weighting, pseudo-labeling and empirical p-value-based filtering to balance skewed and sparse representations of objects in the ground truth data. Results demonstrate the benefits of these different training strategies resulting in an average $F_1=0.661$ and $F_1=0.755$ over the three objects of interest for the 1943 and 1972 imagery, respectively. We also identified that the average size of Waterhole and Big trees increased while the average size of Omuti homesteads decreased between 1943 and 1972 reflecting some of the local effects of the massive post-Second World War economic, agricultural, demographic, and environmental changes. This work also highlights the untapped potential of historical aerial photographs in understanding long-term environmental changes beyond Namibia (and Africa). With the lack of adequate satellite technology in the past, archival aerial photography offers a great alternative to uncover decades-long environmental changes.

Roughly 100 alien abduction cases spanning over the past 30 years are set to be investigated by scientists with hopes of unraveling the mysterious experiences. Researchers at Rice University in Texas plan to analyze a trove of archives consisting of thousands of documents in the form of books, journals, photographs, slides, reports, meeting notes and letters. The cases include the famous story of Betty and Barney Hill, a New Hampshire couple who say they were abducted in 1961 while driving up a mountain. Other cases include one that inspired a new Netflix show - the Pascagoula abduction. The'Archive of the Impossible' at Rice University plays host to material from Jacques Vallee (whose work inspired Steven Spielberg's'Close Encounters of the Third Kind') and author Whitley Streiber, who claimed to have been abducted by aliens in his 1987 book Communion among hundreds of other abduction stories.

'The Sinner' star Bill Pullman reflects on his friendship with late'Spaceballs' co-star John Candy. Mel Brooks had his work cut out for him when he decided to spoof "Star Wars." The legendary comic is making his seventh appearance at the Turner Classic Movies (TCM) Film Festival to present his 1987 film "Spaceballs" on the festival's closing night at TCL Chinese Theatre. The 97-year-old will be joined by TCM host Ben Mankiewicz. Brooks told Fox News Digital that the making of the film quickly racked up the bill, all thanks to one star.

Though last year's writers' and actors' strikes in Hollywood were about myriad factors, fair compensation and residual payments among them, one concern rose far above the others: the encroachment of generative AI – the type that can produce text, images and video – on people's livelihoods. The use of generative AI in the content we watch, from film to television to large swaths of internet garbage, was a foregone conclusion; Pandora's box has been opened. But the rallying cry, at the time, was that any protection secured against companies using AI to cut corners was a win, even if only for a three-year contract, as the development, deployment and adoption of this technology will be so swift. In the mere months since the writers' and actors' guilds made historic deals with the Alliance of Motion Picture and Television Producers (AMPTP), the average social media user has almost certainly encountered AI-generated material, whether they realized it or not. Efforts to curb pornographic AI deepfakes of celebrities have reached the notoriously recalcitrant and obtuse US Congress.

Microsoft Research Asia has unveiled a new experimental AI tool called VASA-1 that can take a still image of a person -- or the drawing of one -- and an existing audio file to create a lifelike talking face out of them in real time. It has the ability to generate facial expressions and head motions for an existing still image and the appropriate lip movements to match a speech or a song. The researchers uploaded a ton of examples on the project page, and the results look good enough that they could fool people into thinking that they're real. While the lip and head motions in the examples could still look a bit robotic and out of sync upon closer inspection, it's still clear that the technology could be misused to easily and quickly create deepfake videos of real people. The researchers themselves are aware of that potential and have decided not to release "an online demo, API, product, additional implementation details, or any related offerings" until they're sure that their technology "will be used responsibly and in accordance with proper regulations."

The vast majority of the popular English named entity recognition (NER) datasets contain American or British English data, despite the existence of many global varieties of English. As such, it is unclear whether they generalize for analyzing use of English globally. To test this, we build a newswire dataset, the Worldwide English NER Dataset, to analyze NER model performance on low-resource English variants from around the world. We test widely used NER toolkits and transformer models, including models using the pre-trained contextual models RoBERTa and ELECTRA, on three datasets: a commonly used British English newswire dataset, CoNLL 2003, a more American focused dataset OntoNotes, and our global dataset. All models trained on the CoNLL or OntoNotes datasets experienced significant performance drops-over 10 F1 in some cases-when tested on the Worldwide English dataset. Upon examination of region-specific errors, we observe the greatest performance drops for Oceania and Africa, while Asia and the Middle East had comparatively strong performance. Lastly, we find that a combined model trained on the Worldwide dataset and either CoNLL or OntoNotes lost only 1-2 F1 on both test sets.

Automatic movie narration targets at creating video-aligned plot descriptions to assist visually impaired audiences. It differs from standard video captioning in that it requires not only describing key visual details but also inferring the plots developed across multiple movie shots, thus posing unique and ongoing challenges. To advance the development of automatic movie narrating systems, we first revisit the limitations of existing datasets and develop a large-scale, bilingual movie narration dataset, Movie101v2. Second, taking into account the essential difficulties in achieving applicable movie narration, we break the long-term goal into three progressive stages and tentatively focus on the initial stages featuring understanding within individual clips. We also introduce a new narration assessment to align with our staged task goals. Third, using our new dataset, we baseline several leading large vision-language models, including GPT-4V, and conduct in-depth investigations into the challenges current models face for movie narration generation. Our findings reveal that achieving applicable movie narration generation is a fascinating goal that requires thorough research.